docs-architect
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard technical writing workflow. No patterns of prompt injection, unauthorized data access, or malicious code execution were found in the SKILL.md instructions or metadata.
- [DATA_EXPOSURE]: The skill instructions involve analyzing codebase structures for documentation purposes. There are no attempts to access sensitive environment variables, system credentials, or user-private keys.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is processing external codebases, which represents an ingestion surface for untrusted data. 1. Ingestion points: Codebase structure and dependencies (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: The skill instructions focus on markdown generation and do not include high-risk capabilities like network access or shell execution. 4. Sanitization: Absent.
Audit Metadata