Skills agent-tools

📦

agent-tools

Name: agent-tools
Author: inf-sh

Content revision r1 Critical 🌐 Network access🔑 Env variables📁 Filesystem access⚙️ External commands

Run Cloud AI Apps with inference.sh

Teams need a consistent way to discover and run hosted AI apps from agent workflows. This skill gives Claude, Codex, and Claude Code practical infsh CLI guidance for discovery, execution, tasks, and authentication.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Do not auto-install this skill.

The canonical policy requires operator review before any installation action.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "agent-tools" from https://skillstore.io/skills/inf-sh-agent-tools.md and its manifest at https://skillstore.io/api/skills/inf-sh-agent-tools/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/inf-sh-agent-tools.md Signed manifest GET /api/skills/inf-sh-agent-tools/manifest Signed lockfile GET /api/skills/inf-sh-agent-tools/lockfile

Test it

Using "agent-tools". Find an image generation option for a product mockup.

Expected outcome:

The assistant lists relevant apps, recommends one candidate, and explains the required prompt fields before execution.

Using "agent-tools". Run a video generation job and check it later.

Expected outcome:

The assistant asks for approval, submits the task, records the task identifier, and describes how to retrieve results.

Using "agent-tools". Choose a hosted search app for research.

Expected outcome:

The assistant compares catalog matches, notes data-sharing concerns, and suggests the app detail command to confirm inputs.

Security Audit

Critical

v4 • 7/5/2026 Open versioned report

The skill is legitimate CLI documentation for inference.sh, but it includes confirmed remote shell installer instructions and many external infsh commands. Most hardcoded documentation links and API-key mentions are false positives, while cloud execution and Twitter/X automation remain meaningful operational risks. No prompt injection text was found in the reviewed files.

Files scanned

540

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (6)

Critical

references/authentication.md:6

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The command pipes a remote HTTPS response directly to sh. This executes unaudited installer code and creates a supply-chain risk.

Critical

references/authentication.md:44

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The reinstall path repeats the curl-to-shell pattern. Re-running a remote script without verification can execute compromised code.

Critical

references/cli-reference.md:6

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The installation command pipes downloaded code directly into sh. This is a high-risk installer pattern unless verified out of band.

Critical

SKILL.md:16

Pipe to shell pattern

curl -fsSL https://cli.inference.sh | sh

The skill instructs users to pipe a downloaded installer directly to sh. This can execute compromised remote code before review.

High

SKILL.md:35-36 SKILL.md:64 SKILL.md:85-86

Social Media Automation Capability

The skill advertises Twitter/X posting and engagement actions. Authorized use could create public posts, direct messages, follows, likes, or reposts.

The referenced lines explicitly list x/post-tweet and other Twitter/X actions. This is clear business-logic risk, not a pattern-only match.

Medium

SKILL.md:22-39 references/running-apps.md:121-129

Remote Processing of User Inputs

The skill sends prompts and input files to hosted AI apps, and file outputs return as cloud URLs. Sensitive data may reach inference.sh and providers.

The examples show remote app runs for images, video, LLMs, search, Twitter, and 3D. The running-apps reference states outputs are returned as URLs.

Capability review items (16)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

SKILL.md:15-18

Ruby/shell backtick execution

```bash

The bash block includes installer and login commands. The Ruby-backtick label is imprecise, but external command execution is real.

Medium

SKILL.md:22-40

Ruby/shell backtick execution

```bash

The bash block lists infsh app run commands that submit prompts and actions to hosted apps. This is intended but real external execution.

Medium

SKILL.md:46-47

Ruby/shell backtick execution

| List all apps | `infsh app list` |

The inline command invokes infsh to list remote apps. Arguments are fixed, so injection risk is low, but external CLI activity is real.

Medium

SKILL.md:47-48

Ruby/shell backtick execution

| Search apps | `infsh app list --search "flux"` |

The inline command runs an infsh search against the app catalog. It is legitimate, but it still executes an external networked CLI.

Medium

SKILL.md:48-49

Ruby/shell backtick execution

| Filter by category | `infsh app list --category image` |

The inline command filters remote app listings through infsh. It has fixed arguments but remains external command execution.

Medium

SKILL.md:49-50

Ruby/shell backtick execution

| Get app details | `infsh app get google/veo-3-1-fast` |

The command retrieves hosted app details through the infsh CLI. This is expected behavior, but it contacts a remote service.

Medium

SKILL.md:50-51

Ruby/shell backtick execution

| Generate sample input | `infsh app sample google/veo-3-1-fast --save input.json` |

The command generates a sample input file through infsh and writes it locally. This is intentional but includes command execution and file output.

Medium

SKILL.md:51-52

Ruby/shell backtick execution

| Run app | `infsh app run google/veo-3-1-fast --input input.json` |

The command runs a hosted AI app with a local input file. It can transmit user data to a cloud service.

Medium

SKILL.md:52-53

Ruby/shell backtick execution

| Run without waiting | `infsh app run <app> --input input.json --no-wait` |

The no-wait command submits remote work and returns before completion. This can create background cloud tasks with user-provided input.

Medium

SKILL.md:53-69

Ruby/shell backtick execution

| Check task status | `infsh task get <task-id>` |

The command retrieves remote task status and results through infsh. It is legitimate but still performs external CLI operations.

Medium

SKILL.md:69-95

Ruby/shell backtick execution

```bash

The related-skills block uses npx to add additional skills from a remote source. This creates a supply-chain and environment-modification risk.

Low

references/authentication.md:6

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

The documentation fetches an installer from https://cli.inference.sh. The URL is part of a remote install flow that requires trusting that host.

Low

references/authentication.md:44

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

The reinstall command fetches the installer from a hardcoded external host. This is expected, but it is still a network trust boundary.

Low

references/cli-reference.md:6

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

The CLI reference fetches an installer from a fixed external URL. The host appears intentional, but users must trust it before installation.

Low

SKILL.md:11

Hardcoded URL

![[inference.sh](https://inference.sh)](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwt

The README embeds a remote image hosted on cloud.inference.sh. Rendering it can trigger an external request, though no malicious domain is evident.

Low

SKILL.md:16

Hardcoded URL

curl -fsSL https://cli.inference.sh | sh

The installation command fetches a script from a fixed external URL. The trust boundary is real because the response is later executed.

Risk Factors

Detected Patterns

Pipe to shell pattern×4

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/inf-sh-agent-tools/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inf-sh-agent-tools/security.svg)](https://skillstore.io/skills/inf-sh-agent-tools?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inf-sh-agent-tools?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inf-sh-agent-tools/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inf-sh-agent-tools.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

inf-sh. (2026). agent-tools security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inf-sh-agent-tools/audits/4

BibTeX citation

@techreport{inf-sh-inf-sh-agent-tools-2026,
  author = {inf-sh},
  title = {agent-tools security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/inf-sh-agent-tools/audits/4},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-tools security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "inf-sh"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inf-sh-agent-tools/audits/4"
identifiers:
  - type: other
    value: "skillstore:inf-sh-agent-tools:audit:4"
    description: "Skillstore immutable audit report identifier"

Compare variants

20 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

tul-sh Recommended

tul-sh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 26

Updated

2026-08-21

toolshell

toolshell-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 23

Updated

2026-08-21

inferen-sh

inferen-sh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 15

Updated

2026-08-21

tool-belt

tool-belt-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 12

Updated

2026-08-21

inferencesh

inferencesh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 12

Updated

2026-08-21

inference-sh-skills

inference-sh-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 11

Updated

2026-08-21

inference-sh-7

inference-sh-7-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 11

Updated

2026-08-21

inf-sh Current

inf-sh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

inference-skills

inference-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

inference-sh-9

inference-sh-9-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

inference-sh-3

inference-sh-3-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

skillssh

skillssh-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

infsh-skills

infsh-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

inference-sh-0

inference-sh-0-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

qu-skills

qu-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

inference-sh-6

inference-sh-6-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

inference-shell

inference-shell-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 6

Updated

2026-08-21

101-skills

101-skills-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 6

Updated

2026-08-21

inference-sh-8

inference-sh-8-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 5

Updated

2026-08-21

halt-catch-fire

halt-catch-fire-agent-tools

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 5

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Run model experiments from the terminal

Use infsh commands to find apps, prepare input, run jobs, and collect results for model testing.

Create media assets with hosted generators

Discover image, video, audio, and 3D apps, then run generation jobs without managing GPUs.

Compare search and LLM providers

Use catalog search and app details to select hosted search or LLM tools for a workflow.

Try These Prompts

Find an app

Use the inference.sh skill to find apps for image generation. Show the safest discovery steps before running anything.

Prepare a run

Help me prepare an infsh run for a video generation app. Generate the sample input first and explain what I must review.

Track a long task

Submit a long-running inference.sh app only after my approval. Then show how to check task status and save the result.

Compare provider options

Compare available LLM and search apps for my workflow. Include authentication needs, data-sharing risks, costs to verify, and recommended commands.

Best Practices

Confirm the app name, provider, input data, and expected cost before running remote work.
Use sample input files and review them before submitting prompts or files.
Require explicit approval before installation, related-skill setup, or Twitter/X actions.

Avoid

Do not pipe remote installer scripts into a shell without verification.
Do not paste secrets, private files, or regulated data into remote app inputs without approval.
Do not automate posts, messages, follows, likes, or reposts without final human review.