doc-sectest-audit
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill package does not contain local script files; it provides a workflow configuration and references an external path for the audit tool.
- [PROMPT_INJECTION]: The skill processes markdown documentation, which presents a surface for indirect prompt injection. This risk is managed by an internal safety policy. Ingestion points: External markdown files passed to the audit command (SKILL.md). Boundary markers: None defined. Capability inventory: Orchestrates the execution of doc-sectest-validator and doc-sectest-reviewer (SKILL.md). Sanitization: The unsafe-guidance policy explicitly blocks the generation of instructions that enable operational misuse.
Audit Metadata