fix-ci
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes CI logs, which are considered untrusted data because they may contain attacker-controlled output from external pull requests.
- Ingestion points: The skill reads failure logs in Step 2 of the workflow using the
ghCLI. - Boundary markers: The instructions specifically mandate the use of
wrapUntrustedCliResponsefromsrc/agents/prompt-helpers.tsto delimit untrusted content. - Capability inventory: The skill utilizes the GitHub CLI (
gh) for repository management and delegates code modifications to other agent modules. - Sanitization: The prompt includes explicit instructions to treat embedded commands within logs as data rather than instructions.
Audit Metadata