skills/tw93/pake/code-review/Gen Agent Trust Hub

code-review

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes PR diffs via 'gh pr diff', which is a surface for indirect prompt injection. This is the primary purpose of the tool. 1. Ingestion points: Output from 'gh pr diff' (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Bash, Read, Grep, Glob tools. 4. Sanitization: None specified.
  • [COMMAND_EXECUTION]: Uses standard development tools like pnpm and vitest for project maintenance tasks like building and testing. These are benign utility commands consistent with the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 10:49 AM
Security Audit — agent-trust-hub — code-review