Meal Planner
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes user-controlled data from multiple markdown files, which are then used to generate meal plans and shopping lists.
- Ingestion points: The skill reads from user-editable files located in
~/Clawic/data/meal-planner/recipes/,~/Clawic/data/meal-planner/inventory/, and thememory.mdpreferences file. - Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the agent when processing these external data files, increasing the risk of the agent following instructions embedded within the data.
- Capability inventory: The skill is granted read and write access to the
~/Clawic/data/meal-planner/directory and its subfolders. - Sanitization: There is no evidence of content sanitization or validation logic to filter out potentially malicious prompt instructions in user-provided files.
Audit Metadata