comet-github-ci-triage
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the GitHub CLI (
gh pr checksandgh run view --log-failed) to retrieve build status and logs. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external data.
- Ingestion points: Data enters the agent context through
ghcommand output (PR check names, states, and failure logs), Codecov API metadata, and the local file../comet-github/references/maintainer-contract.md. - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between raw log content and the agent's core instructions.
- Capability inventory: The agent has the capability to execute shell commands (
gh) and is directed to interface with other tools likecomet-github-issue-fixandcomet-safe-deliveryfor remediation. - Sanitization: There is no mention of sanitizing, escaping, or filtering the content retrieved from external logs or API metadata before the agent evaluates it.
Audit Metadata