sample-size-and-power-planning-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown documentation and instructional guidelines. No malicious patterns, executable code, or network operations were identified. It references the author's own GitHub repository (aipoch/medical-research-skills), which is a legitimate vendor resource.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided clinical study parameters, creating an ingestion surface. However, the skill lacks any capabilities (such as code execution, file writing, or network access) that would allow exploitation. Ingestion points: user queries in SKILL.md. Boundary markers: clarified in references/input-clarification-thresholds.md. Capability inventory: none. Sanitization: rigid output structures mandated by references/hard-rules.md.
Audit Metadata