gh-fix-ci
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the local system by executing the
gitandgh(GitHub CLI) binaries via Python'ssubprocessmodule to retrieve repository status, PR checks, and build logs. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from external sources which could be used to influence agent behavior.
- Ingestion points: Build logs are fetched from GitHub Actions via the
ghCLI and the GitHub API inscripts/inspect_pr_checks.py. - Boundary markers: Log output is not wrapped in special delimiters or accompanied by instructions to ignore embedded commands.
- Capability inventory: The skill allows the agent to propose and apply code changes to the local repository.
- Sanitization: No sanitization is performed on the log content to remove potential prompt injection sequences.
- Mitigation: The risk is limited as the skill's workflow explicitly requires the agent to obtain human approval before implementing any suggested fixes.
Audit Metadata