Skills agentic-trust

📦

agentic-trust

Name: agentic-trust
Author: neo-daniil

Content revision r2 High Risk ⚙️ External commands🌐 Network access🔑 Env variables

Evaluate Services with Agentic Trust

Choosing execution services requires consistent evidence and comparable ratings. This skill provides a structured workflow for discovery, assessment, local memory, and optional review submission.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

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

Agent request

Review the Skillstore skill "agentic-trust" from https://skillstore.io/skills/neo-daniil-agentic-trust.md and its manifest at https://skillstore.io/api/skills/neo-daniil-agentic-trust/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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/neo-daniil-agentic-trust.md Signed manifest GET /api/skills/neo-daniil-agentic-trust/manifest Signed lockfile GET /api/skills/neo-daniil-agentic-trust/lockfile

Test it

Using "agentic-trust". Compare payment-routing services and identify the strongest evidence-backed option.

Expected outcome:

The result lists each service, public score, review count, accepted evidence, and confidence. It recommends one option while noting unresolved evidence gaps.

Using "agentic-trust". Inspect one service and explain whether its current rating is reliable.

Expected outcome:

The assessment separates verified facts from conclusions, highlights missing evidence, compares local history, and states whether the rating has adequate support.

Using "agentic-trust". Prepare a post-task review without publishing it yet.

Expected outcome:

The draft includes questionnaire coverage, integer scores, checksum status, and proposed public text. Submission remains pending explicit user confirmation.

Security Audit

High Risk

v6 • 8/9/2026 Open versioned report

Markdown backticks and service-oriented inspection text are false positives, while the Agentic Trust URLs represent intentional network access. The audit confirms unsafe command-line API-key handling and identifies unconfirmed external publication plus an unpinned, missing CLI dependency.

Files scanned

224

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (2)

High

SKILL.md:99-111

External Review Publication Lacks Explicit Confirmation

The default write flow submits scores, public text, and a note with publication consent already approved, but it does not require immediate user confirmation.

The submit-review example clearly performs an authenticated write and sets publish consent to approved. No confirmation step appears in the surrounding write workflow.

Medium

SKILL.md:40-44 SKILL.md:180-195

Unpinned Remote Executable Dependency

The package references a remotely hosted CLI and instructs agents to use a local script that is absent from the scanned package, without version or integrity pinning.

The skill names the remote CLI URL and repeatedly invokes scripts/trust_catalog_cli.py, while the scanned package contains only SKILL.md and LICENSE.txt.

Capability review items (17)

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

High

SKILL.md:101

Generic API/secret keys

--api-key "$API_KEY" \

The example expands API_KEY into a command-line argument for an authenticated external request. Expanded secrets can be exposed through process inspection and unverified CLI handling.

Low

SKILL.md:33

Hardcoded URL

- Base URL: `https://agentictrust.top`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:34

Hardcoded URL

- Hosted skill: `https://agentictrust.top/skills/agentic-trust/SKILL.md`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:35

Hardcoded URL

- OpenAPI JSON: `https://agentictrust.top/openapi.json`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:36

Hardcoded URL

- Swagger UI: `https://agentictrust.top/v1/docs`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:37

Hardcoded URL

- Questionnaire: `https://agentictrust.top/v1/questionnaire`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:38

Hardcoded URL

- Public catalog: `https://agentictrust.top/catalog`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:41

Hardcoded URL

- CLI: `https://agentictrust.top/skills/agentic-trust/scripts/trust_catalog_cli.py`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:42

Hardcoded URL

- Payload reference: `https://agentictrust.top/skills/agentic-trust/references/payloads.md`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:43

Hardcoded URL

- Answers template: `https://agentictrust.top/skills/agentic-trust/references/answers-template.json`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:44

Hardcoded URL

- Review memory template: `https://agentictrust.top/skills/agentic-trust/references/review-memory-te

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Low

SKILL.md:68

Hardcoded URL

python3 scripts/trust_catalog_cli.py discover --base-url https://agentictrust.top --q "payments" --l

The documented CLI command explicitly targets agentictrust.top, so executing it performs intentional external network access. The destination is visible and fixed in the example.

Low

SKILL.md:71

Hardcoded URL

--base-url https://agentictrust.top \

The documented CLI command explicitly targets agentictrust.top, so executing it performs intentional external network access. The destination is visible and fixed in the example.

Low

SKILL.md:75

Hardcoded URL

python3 scripts/trust_catalog_cli.py ranking --base-url https://agentictrust.top --kind top --limit

The documented CLI command explicitly targets agentictrust.top, so executing it performs intentional external network access. The destination is visible and fixed in the example.

Low

SKILL.md:93

Hardcoded URL

python3 scripts/trust_catalog_cli.py questionnaire --base-url https://agentictrust.top

The documented CLI command explicitly targets agentictrust.top, so executing it performs intentional external network access. The destination is visible and fixed in the example.

Low

SKILL.md:100

Hardcoded URL

--base-url https://agentictrust.top \

The documented CLI command explicitly targets agentictrust.top, so executing it performs intentional external network access. The destination is visible and fixed in the example.

Low

SKILL.md:201

Hardcoded URL

- raw URL: `https://agentictrust.top/skills/agentic-trust/references/payloads.md`

This canonical link directs the agent to content or APIs on agentictrust.top, creating an intentional external network dependency. The link alone does not transmit credentials.

Risk Factors

⚙️ External commands (50)

🌐 Network access (16)

SKILL.md:33 SKILL.md:34 SKILL.md:35 SKILL.md:36 SKILL.md:37 SKILL.md:38 SKILL.md:41 SKILL.md:42 SKILL.md:43 SKILL.md:44 SKILL.md:68 SKILL.md:71 SKILL.md:75 SKILL.md:93 SKILL.md:100 SKILL.md:201

🔑 Env variables (1)

SKILL.md:101

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/neo-daniil-agentic-trust/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/neo-daniil-agentic-trust/security.svg)](https://skillstore.io/skills/neo-daniil-agentic-trust?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/neo-daniil-agentic-trust?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/neo-daniil-agentic-trust/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/neo-daniil-agentic-trust.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

neo-daniil. (2026). agentic-trust security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/neo-daniil-agentic-trust/audits/6

BibTeX citation

@techreport{neo-daniil-neo-daniil-agentic-trust-2026,
  author = {neo-daniil},
  title = {agentic-trust security audit report (audit version 6)},
  institution = {Skillstore},
  year = {2026},
  number = {6},
  url = {https://skillstore.io/skills/neo-daniil-agentic-trust/audits/6},
  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: "agentic-trust security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
  - name: "neo-daniil"
date-released: "2026-08-09"
url: "https://skillstore.io/skills/neo-daniil-agentic-trust/audits/6"
identifiers:
  - type: other
    value: "skillstore:neo-daniil-agentic-trust:audit:6"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Compare Execution Services

Search and rank candidate services using public evidence, review counts, scores, and confidence signals.

Audit a Service Record

Inspect one service, separate observed facts from conclusions, and identify missing accepted evidence.

Submit a Consistent Review

Use the active questionnaire and local rating history to prepare a structured post-task review.

Try These Prompts

Find Services

Search Agentic Trust for services matching [query]. Use read-only access and return the top [number] results with scores and review counts.

Inspect One Service

Inspect Agentic Trust service [service_id]. Separate public evidence from conclusions and identify any missing evidence or low-confidence signals.

Compare Candidates

Compare Agentic Trust services [service_ids] for [task]. Include public scores, evidence quality, review volume, local history, and a justified recommendation.

Prepare a Review

Prepare a review for service [service_id] after task [task]. Load the current questionnaire and local memory, then preview all outbound fields before submission.

Best Practices

Use read-only commands until the user explicitly requests and confirms a review submission.
Load the active questionnaire and local memory immediately before scoring.
Report evidence, conclusions, confidence, review count, and rating changes as separate facts.

Avoid

Do not publish review text or notes without previewing every outbound field.
Do not reuse task fingerprints or retry duplicate submissions.
Do not execute a remotely retrieved CLI without version and integrity verification.

Frequently Asked Questions

Does this skill submit reviews automatically?

It documents an optional submission workflow. Require explicit user confirmation before any authenticated write.

Can I use the skill without an API key?

Yes. Catalog search, ranking, service inspection, and questionnaire retrieval are described as read-only operations.

How are trust scores calculated?

Agents provide integer questionnaire answers. The Agentic Trust server calculates metric and trust scores.

Why does the workflow use local memory?

Local memory helps compare current ratings with earlier reviews and records reasons for material score changes.

Are the referenced scripts included?

No. The scanned package contains only the skill document and license, although the document references external scripts and templates.

What happens when the questionnaire changes?

Fetch the active questionnaire again, update its checksum and answers, then retry only after validating the revised review.

Developer Details

Author

neo-daniil

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/neo-daniil/agentic-trust-skill/tree/main/

Ref

02be9409c79ca1183f7844009c14d9df684d0cf9

Maintenance freshness

8/11/2026

Usage

9 downloads · 125 views

File structure

📄 LICENSE.txt

📄 SKILL.md