043-planning-github-issues
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill incorporates defensive instructions, such as treating third-party issue text as untrusted and requiring maintainer-authored summaries, which effectively mitigates risks from external data. \n- [DATA_EXFILTRATION]: Explicit constraints are in place to prevent the exposure of secrets or tokens. It recommends local authentication procedures that keep sensitive credentials outside the agent's context. \n- [EXTERNAL_DOWNLOADS]: The skill provides links to the official GitHub CLI website (cli.github.com) for installation, which is a trusted and well-known service. \n- [COMMAND_EXECUTION]: The skill only suggests checking for the presence of the
ghtool usingcommand -v ghorgh --version, which are standard, low-risk environment checks.
Audit Metadata