check-ci
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes git and gh (GitHub CLI) commands to retrieve repository context, PR details, and CI workflow results. These commands are necessary for the skill's primary function of reporting development status.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its data ingestion process.\n
- Ingestion points: CI failure logs are retrieved using
gh run view --log-failedand PR review/comment counts are fetched viagh api. These sources can contain content generated by external contributors or automated processes.\n - Boundary markers: The skill does not implement delimiters or specific instructions to the agent to treat the ingested CI logs or comment metadata as non-executable data.\n
- Capability inventory: The skill allows the agent to execute shell commands and suggests further automated repair actions such as
/fix-cior/fix-conflictbased on the status it reads.\n - Sanitization: There is no evidence of filtering or escaping performed on the content retrieved from GitHub before it is passed to the agent context.
Audit Metadata