ideate
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted user input during the ideation process.
- Ingestion points: User-supplied problem descriptions and titles are ingested in Step 1 of the
SKILL.mdfile and used to generate the document content and filename. - Boundary markers: The instructions lack explicit boundary markers or system instructions to ignore potential commands embedded within the user's input.
- Capability inventory: The skill possesses the capability to read directory listings (
ls) and write/create files (docs/ideation/NNN_short-name.mdandINDEX.md). - Sanitization: There is no explicit requirement for the agent to sanitize or validate the user-provided title or description. This could lead to path manipulation or secondary injection if the agent uses these values insecurely during file creation or index updating.
Audit Metadata