alterlab-string-db
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external API which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Functions in
scripts/string_api.pyfetch data from the STRING Database REST API (string-db.org). - Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded in the retrieved scientific data.
- Capability inventory: The skill has access to
Bash(python:*),Bash(curl:*),WebFetch, andRead, allowing for significant system interaction with the fetched data. - Sanitization: There is no evidence of sanitization, validation, or filtering of the content returned by the STRING API before it is processed by the agent.
Audit Metadata