loop-on-ci
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) to monitor PR checks and retrieve CI logs. The commandsgh pr view,gh pr checks, andgh run vieware core to its functionality for identifying and resolving build failures. These are well-known tools from a trusted service used here for their intended purpose. - [PROMPT_INJECTION]: The skill processes external data via CI logs, creating a surface for indirect prompt injection.
- Ingestion points: CI logs fetched through
gh run view <run-id> --log-failedas specified in the workflow. - Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from obeying instructions potentially embedded within the log output.
- Capability inventory: The agent is expected to fix failures, which involves code modification and repository updates.
- Sanitization: There is no evidence of sanitization or content validation for the logs being processed.
Audit Metadata