grocery-shopping
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user in the form of recipes and pantry inventory lists. This represents a potential surface for indirect prompt injection where malicious instructions could be embedded within a recipe to influence the agent's behavior.
- Ingestion points: User-provided recipe text and pantry inventory status.
- Boundary markers: The skill does not define explicit delimiters for untrusted recipe data.
- Capability inventory: No network operations, file system writes, or subprocess execution capabilities are requested or used.
- Sanitization: No explicit sanitization or validation of the recipe content is described.
- [NO_CODE]: The skill consists entirely of markdown-based instructions for the LLM. It does not include any executable scripts, configuration files, or external dependencies that could facilitate traditional technical attacks.
Audit Metadata