github-gitea-actions
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional markdown and configuration files without any executable scripts or binary files, significantly reducing the attack surface.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external repository data (workflow files) which constitutes an indirect prompt injection surface. However, the instructions explicitly mandate defensive measures:
- Ingestion points: Processes existing YAML files in
.github/workflows/and.gitea/workflows/. - Boundary markers: Encourages documentation and comments (e.g.,
# vX.Y.Z) to clarify immutable references. - Capability inventory: The skill is purely instructional and does not possess its own subprocess or network execution capabilities.
- Sanitization: Specifically instructs the agent to 'avoid interpolating untrusted event data directly into shell commands,' which is a direct mitigation for injection attacks in CI/CD environments.
Audit Metadata