string-database-ppi
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves protein-protein interaction data, functional enrichment statistics, and network visualizations from the official STRING database API at string-db.org.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the external STRING database API to perform network analysis and functional enrichment. This ingestion represents a potential attack surface for indirect prompt injection if the remote database content were to be maliciously manipulated.
- Ingestion points: API responses from string-db.org are ingested across SKILL.md and references/api_advanced.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic for the external data.
- Capability inventory: The skill includes capabilities to perform network requests and write image files to the local file system.
- Sanitization: Data is parsed using standard json and pandas library functions without additional content-based filtering.
Audit Metadata