wiki-recipe
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process recipe data from external, untrusted sources (URLs or text) to create vault notes.
- Ingestion points: Processes external recipe sources provided by the user at runtime.
- Boundary markers: There are no explicit instructions or delimiters defined to isolate the ingested data or prevent the agent from obeying instructions embedded within recipe text.
- Capability inventory: The skill uses IWE MCP tools to perform file system writes (
pages/directory) and queries (iwe-query). - Sanitization: No explicit sanitization or validation of the ingested content is described before it is written to the vault or used in the agent's logic.
Audit Metadata