github-research
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides documentation for executing GitHub CLI (
gh) commands to search issues, pull requests, and code. These commands are standard for repository research and are used to fetch information rather than modify system state. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources (GitHub issues and PRs). While this data is attacker-controlled, the risk is mitigated by the skill's instructions to use structured JSON output and format the results into a human-readable report, which reduces the likelihood of the agent interpreting data as instructions.
Audit Metadata