ppi-string-query

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a standard data-retrieval tool for biological research. Analysis of the scripts and instructions confirms that its behavior is consistent with its stated purpose of protein interaction analysis.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its data-ingestion capabilities from external sources.\n
  • Ingestion points: The skill accepts a uniprot_id parameter and processes the resulting interaction data from the STRING database API.\n
  • Boundary markers: No delimiters or protective markers are used to encapsulate the external data within the agent's context.\n
  • Capability inventory: The ppi_string_request tool executes network requests to external domains to fetch protein records.\n
  • Sanitization: There is no evidence of validation or sanitization of the input protein IDs or the returned database output.\n- [EXTERNAL_DOWNLOADS]: The skill connects to string-db.org to retrieve interaction data. This is a well-known and trusted scientific resource, and the usage is integral to the skill's primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 05:58 AM