note-it
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data from specification documents and source code to generate implementation notes.
- Ingestion points: Specification files (e.g., tasks/prd-*.md) and implementation source code.
- Boundary markers: None specified; the skill lacks instructions to treat content from processed files as data rather than instructions.
- Capability inventory: The skill possesses the capability to write and modify files in the docs/ directory and create new directories.
- Sanitization: No sanitization or escaping of the ingested content is performed before it is placed into the HTML template, creating a surface for both prompt injection and potential HTML injection.
- [COMMAND_EXECUTION]: The skill requires the agent to perform system operations including checking directory existence, auto-creating directories, and writing formatted files to the local file system.
Audit Metadata