gh-fix-ci
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/inspect_pr_checks.pyuses thesubprocessmodule to executegitandghcommands. This is used to resolve repository paths, verify authentication status, and fetch PR check information. The implementation usesshell=Falseand validates certain inputs (like run IDs) using regular expressions to prevent shell injection. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
- Ingestion points: External data is ingested from GitHub Actions logs in
scripts/inspect_pr_checks.pyusinggh run view --logand the GitHub API. - Boundary markers: No explicit delimiters or boundary markers are used to isolate the untrusted log content from the agent's primary instructions.
- Capability inventory: The skill has the capability to execute CLI commands and modify the repository contents as part of its fix implementation workflow.
- Sanitization: The skill does not perform sanitization of log content to remove or neutralize potentially malicious natural language instructions before processing.
Audit Metadata