clinical-diagnostic-reasoning
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions, process flows, and evaluation metadata. No executable scripts, binaries, or automated shell commands are included in the package.- [EXTERNAL_DOWNLOADS]: The skill references an external repository at github.com/aipoch/medical-research-skills for source attribution. This reference targets a well-known service and belongs to the stated author, posing no risk of remote code execution.- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests untrusted 'New patient presentation' data (SKILL.md). However, the risk is negligible because: 1. Ingestion point: Patient presentation input. 2. Boundary markers: The 'Input Validation' section provides explicit instructions to refuse out-of-scope requests. 3. Capability inventory: The skill possesses no tools or scripts for network access, file system writes, or command execution. 4. Sanitization: While formal sanitization is absent, the workflow relies on reasoning constraints that do not involve downstream code execution.
Audit Metadata