1k-monitor-pr-ci
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) and Git commands to fetch pull request metadata, CI status, and logs. It also has the capability to modify the local filesystem and push changes back to the remote repository. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by design, as it ingests and processes external, untrusted content.
- Ingestion points: Retrieves PR comments via
gh apiand fetches CI failure logs usinggh run view --log-failed. - Boundary markers: The workflow does not specify delimiters or instructions to ignore embedded commands within the fetched comments or logs.
- Capability inventory: The agent can perform file system writes to 'fix the code', execute
git commit, and performgit pushto the repository. - Sanitization: There is no mention of sanitization or validation of the text retrieved from GitHub before it is used to determine code changes.
Audit Metadata