audit-actions
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a security audit guide. It does not contain any executable scripts, binary files, or hidden commands. The provided YAML frontmatter correctly restricts the skill's environment by declaring no network or filesystem write capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from external workflow files (
.github/workflows/). While this represents a data ingestion surface, the skill provides a structured audit template and does not introduce any new executable capabilities that could be leveraged by malicious content in the audited files. - Ingestion points: GitHub workflow files located at
.github/workflows/(referenced in SKILL.md). - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No internal capabilities (exec, network, or file writes) are included in the skill (permissions.yaml).
- Sanitization: None specified for the audit process.
Audit Metadata