capture-idea
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's primary function is to manage local text files for project planning. It lacks the ability to make network requests, execute system commands, or download external code.
- [INDIRECT_PROMPT_INJECTION]: The skill reads data from
./ideas/CONTEXT.md, which is a surface for indirect prompt injection. However, the logic is limited to appending text in a specific format. - Ingestion points: The agent reads the contents of
./ideas/CONTEXT.mdin step 2. - Boundary markers: None present.
- Capability inventory: The agent can read and write to the local filesystem (specifically creating or appending to markdown files).
- Sanitization: No sanitization is performed on the input from the file.
- [NO_CODE]: The skill contains no executable code, script files, or software package definitions.
Audit Metadata