deerpark
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from a public API, which creates a vulnerability surface where malicious instructions could be embedded in the fetched text.
- Ingestion points: The skill frequently fetches data from
https://deerpark.appin JSON, Markdown, and HTML formats (referenced inSKILL.mdandreferences/endpoints.md). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are provided to the agent when processing this external content.
- Capability inventory: The skill instructs the agent to use
curlfor network requests,jqfor data manipulation, and file-writing capabilities (e.g., saving to/tmp/allworks.jsoninreferences/recipes.md). - Sanitization: There are no instructions for sanitizing or escaping the content retrieved from the API before it is processed by the agent.
Audit Metadata