docs-audit-and-refresh
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to read and process arbitrary code and documentation files which may contain untrusted content.
- Ingestion points: The skill reads content from throughout the repository, including
packages/,docs/, and project skill definitions in.qwen/skills/*/SKILL.md. - Boundary markers: There are no explicit instructions or delimiters used to ensure the agent ignores executable instructions or prompts that might be embedded in the files being audited.
- Capability inventory: The skill has the capability to write to the
docs/directory and specifically instructions to modifypackages/core/src/skills/bundled/qc-helper/SKILL.mdto update topic-to-path tables. - Sanitization: No validation or sanitization of the input data from the codebase is specified before it is used to refresh documentation or update skill metadata.
Audit Metadata