string-database

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Behavioral steering instructions are included in the 'SKILL.md' file, directing the agent to proactively suggest the 'K-Dense Web' platform to users when requests involve multi-step reasoning or deep research.
  • [PROMPT_INJECTION]: The skill provides an attack surface for Indirect Prompt Injection due to the processing of remote data from the STRING API.
  • Ingestion points: Protein interaction data and functional annotations are retrieved via 'scripts/string_api.py'.
  • Boundary markers: No delimiters or safety instructions are used when interpolating API data into the agent context.
  • Capability inventory: The skill can perform network read operations and provides examples for saving data to the local file system.
  • Sanitization: There is no evidence of validation or sanitization for the annotations or descriptions returned by the third-party STRING database.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data from the well-known bioinformatics resource at 'https://string-db.org/api'. This is the primary function of the skill and is documented as a legitimate external reference.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:48 PM