pr
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub pull requests, which could contain malicious instructions designed to subvert agent behavior. \n
- Ingestion points: The skill is instructed to read pull request descriptions, comments, commit messages, and linked issues via
$ARGUMENTSand GitHub CLI tools (SKILL.md). \n - Boundary markers: No specific delimiters or instructions are provided to isolate external content or warn the agent to ignore instructions embedded within pull request text. \n
- Capability inventory: The skill utilizes
gh pr diff,gh pr view,gh api, andgit showto access repository information. \n - Sanitization: No sanitization, filtering, or validation of the fetched content is described. \n- [COMMAND_EXECUTION]: The skill uses local command-line tools to interact with GitHub repositories to perform its tasks. \n
- Evidence: Instructions include using
gh pr diff,gh pr view,gh api, andgit show <ref>:<path>to retrieve data for analysis. While standard for the skill's purpose, these tools represent the primary capabilities accessible to the agent.
Audit Metadata