docs-architect
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data (codebases) to generate documentation.
- Ingestion points: The documentation process describes analyzing codebase structures, dependencies, and design patterns (SKILL.md).
- Boundary markers: There are no explicit instructions to the agent to ignore instructions embedded within the codebase comments or data files during analysis.
- Capability inventory: The skill involves reading files and generating structured markdown output, but does not explicitly request high-privilege capabilities like network access or shell execution.
- Sanitization: No sanitization or validation of the input codebase content is specified, making the agent susceptible to instructions hidden within the source code.
Audit Metadata