Versioned security assessment

Report ID: SA-F3892A43

8/21/2026, 8:33:56 AM

find-skills security assessment v1

Skill Security Certification Report

Audit History
Scanner version 3.0.0 Audit model: codex Latest published report
Skill name
find-skills
Version
v1
Maintainer
brianlovin
Source
github.com/brianlovin/agent-config/tree/1a9819ebf3fee811150fc76cbe177ea4e5f747ff/skills/find-skills
Coverage
1 Files scanned · 134 Lines analyzed
Policy version
skillstore-security-audit-policy-v1

Highest confirmed finding severity

High

1 confirmed security finding requires attention.

Installation context

Check the current Skill page

This page summarizes report evidence only. The Skill page provides the canonical install advisory.

Open current Skill page

This report does not block or authorize the manifest or ZIP.

Most static alerts are false positives caused by Markdown backticks and public documentation links. The skill intentionally runs the Skills CLI and can globally install an unverified third-party skill while bypassing confirmation. Source review and explicit installation approval are required.

Report position

Latest published report

Latest refers to the report sequence, not to artifact currentness.

Audit attestation

Active attestation

A public attestation is available for this exact report.

Human verification

Not verified

No human verification is recorded for this report.

Coverage

1 Files scanned · 134 Lines analyzed

6 items shown for review

Limitations

This report does not claim runtime or sandbox execution and does not prove the absence of side effects.

Evidence chain

Follow the evidence from source binding to the install contract. Available evidence supports verification; it is not a safety guarantee.

  1. Source

    Commit and path bound

  2. Artifact

    Content and tree hashes bound

  3. Audit

    Complete

  4. Install contract

    Open manifest to verify

    Open manifest

Capabilities observed

Observed means this report recorded supporting evidence. Not recorded does not prove that a capability is absent.

Contains scripts

May execute code included with the Skill.

Not recorded by this audit

Network access

May connect to external services.

Observed in 3 evidence locations

Filesystem access

May read or write local files.

Not recorded by this audit

Env variables

May read values from the process environment.

Not recorded by this audit

External commands

May invoke commands or programs outside the Skill.

Observed in 20 evidence locations

Capability review items (5)
High
SKILL.md:91-93
Ruby/shell backtick execution
```bash
Lines 89-93 instruct the agent to run a global installation command with confirmation disabled. It installs a discovered third-party skill and changes persistent user-level state.
Medium
SKILL.md:48-50
Ruby/shell backtick execution
```bash
Lines 46-50 explicitly direct the agent to run npx skills find. This invokes an external npm CLI and may download the package when it is unavailable locally.
Medium
SKILL.md:54-55
Ruby/shell backtick execution
- User asks "how do I make my React app faster?" → `npx skills find react performance`
Line 54 supplies a concrete npx search invocation for the agent workflow. Running it executes an external npm CLI, although the example query is benign.
Medium
SKILL.md:55-56
Ruby/shell backtick execution
- User asks "can you help me with PR reviews?" → `npx skills find pr review`
Line 55 supplies a concrete npx search invocation for the agent workflow. Running it executes an external npm CLI, although the example query is benign.
Medium
SKILL.md:56-60
Ruby/shell backtick execution
- User asks "I need to create a changelog" → `npx skills find changelog`
Line 56 supplies a concrete npx search invocation for the agent workflow. Running it executes an external npm CLI, although the example query is benign.

Risk findings

Confirmed security concerns are separated from items that still need review.

Confirmed security concerns (1)

RISK-001 High
SKILL.md:87-95
Unverified Global Skill Installation
The workflow offers to install a discovered third-party skill globally with -y, without source verification or content review. Disabling confirmation can persist malicious skill instructions.
Lines 87-95 explicitly direct the agent to install the selected package globally and explain that -y skips confirmation. No verification step appears before installation.

Remediation

Suggested fixes recorded by this audit. Applying them is the maintainer’s responsibility.

  1. FIX-001
    High
    The installation workflow uses global scope and disables CLI confirmation.
    Remove -y, avoid global installation by default, and request explicit user approval immediately before executing the final command.
  2. FIX-002
    High
    Discovered third-party skills are offered for installation without source or content verification.
    Inspect the resolved repository, commit, skill contents, permissions, and security report before recommending or installing a result.

Expert evidence

Immutable subject identity, scanner metadata, dismissed matches, and source-level evidence.

Artifact subject

Marketplace commit
f3892a43246af3d370b4fd76c40c2c2712b351f6
Content hash
54b44dc9539df865fbb060f62fb062e8232e765852a0cf14c38301fe0c1eb264
Tree hash
9fbfdbf96eb1e47adccf2f9a4dc9162400c78f36abf304b4c5e0f9bdfaddce92
Skill path
skills/brianlovin/find-skills
Audit payload hash
0cb582f6b6bfd251b5d850a524c5d899

Analysis metadata

Audit model: codex

Analysis state: Complete

Scope is limited to the recorded files, lines, methods, and evidence. No runtime or sandbox execution is claimed.

Verify and export

JSON report Signed attestation CITATION.cff SARIF 2.1.0 Signed installation manifest Source

The manifest and lockfile bind install artifacts to cryptographic hashes. This integrity claim is separate from the security assessment.

Audit attestation: active