dbsnp-database
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external genetic variant data from the NCBI dbSNP API, which creates a surface for potential indirect prompt injection if the API returns untrusted or adversarial content.
- Ingestion points: Data is retrieved from NCBI E-utilities (eutils.ncbi.nlm.nih.gov) and the Variation Services API (api.ncbi.nlm.nih.gov) in XML and JSON formats as demonstrated in SKILL.md.
- Boundary markers: Absent; the skill's code snippets do not implement specific delimiters or instructions to isolate the external data from the agent's core logic.
- Capability inventory: SKILL.md documents network access (requests.get, requests.post) and file-writing capabilities (pandas.to_csv, matplotlib.savefig).
- Sanitization: Absent; the skill does not describe or implement validation or filtering logic for the incoming data from the remote APIs.
Audit Metadata