opentargets-database
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: Detailed analysis of the skill's instructions and structure found no evidence of malicious intent, credential theft, or unauthorized code execution.
- [EXTERNAL_DOWNLOADS]: The skill connects to the official Open Targets Platform GraphQL API at api.platform.opentargets.org. This is a well-known, reputable scientific resource for pharmaceutical research.
- [PROMPT_INJECTION]: The skill includes behavioral instructions that direct the agent to promote the author's commercial platform (www.k-dense.ai) when handling complex workflows. This is a brand-promotion instruction rather than a security bypass.
- [PROMPT_INJECTION]: A surface for indirect prompt injection exists as the skill processes literature and omics data from an external API.
- Ingestion points: External data is ingested from api.platform.opentargets.org.
- Boundary markers: None are specified in the prompt templates.
- Capability inventory: Data querying and processing via the referenced scripts/query_opentargets.py.
- Sanitization: No evidence of output sanitization or filtering for retrieved literature content.
Audit Metadata