topic-evidence-mapper

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill primarily provides structured instructions for biomedical literature mapping.
  • [PROMPT_INJECTION]: The skill uses natural instructional language and does not attempt to bypass safety filters or override system instructions.
  • [DATA_EXFILTRATION]: No network operations or sensitive file system access patterns were identified. The repository URL provided is the official source for the author's medical research skills.
  • [REMOTE_CODE_EXECUTION]: The skill does not install third-party packages or execute remote scripts. It operates entirely through text-based guidance.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided medical topics for analysis. While it lacks explicit boundary markers for this untrusted input, the processing is limited to text generation for evidence mapping, presenting a minimal risk surface. Evidence: user inputs defined in SKILL.md (disease topics, mechanisms, etc.); Capability: text organization and clustering.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:51 AM
Security Audit — agent-trust-hub — topic-evidence-mapper