prototype-comments
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection surface via local data ingestion.
- Ingestion points: The skill reads modification intent and positioning data from
src/prototypes/<prototype-id>/.spec/prototype-comments.json. - Boundary markers: There are no markers or instructions provided to the agent to help it distinguish between legitimate project data and potential malicious instructions within the JSON file.
- Capability inventory: The agent has the authority to modify source code implementation files in
src/prototypes/and delete files within the.spec/directory based on the JSON content. - Sanitization: The skill does not define any validation or sanitization steps for the input data before it is used to guide the agent's code editing or file deletion tasks.
Audit Metadata