document-it
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository files such as code, READMEs, and runbooks to generate or update documentation. This creates an attack surface where malicious instructions embedded in the repository content could influence the agent's behavior or output.
- Ingestion points: Reads repository files including source code, existing markdown documentation, and DocSlime-specific files (
SKILL.md). - Boundary markers: None identified. The instructions do not provide delimiters or specific "ignore embedded instructions" warnings for the agent when processing these files.
- Capability inventory: The skill is authorized to perform surgical diffs and write/update documentation files throughout the repository (
SKILL.md). - Sanitization: The skill includes a specific safety instruction to ensure "No secrets" are included in the documentation.
- [EXTERNAL_DOWNLOADS]: The skill mentions the use of a tool-specific installation command,
docslime-install, which appears to be a prerequisite for the DocSlime documentation framework mentioned in the workflow. - Evidence:
SKILL.mdrefers todocslime-installas part of the tooling used for initializing and filling documentation structures.
Audit Metadata