immunity
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and heuristics for manuscript evaluation. It contains no scripts, binary executables, or commands that could be executed on a host system.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data (manuscripts), which constitutes an ingestion point for untrusted content. However, the skill lacks any dangerous capabilities (such as file system writes, network operations, or subprocess execution) that could be leveraged by a malicious payload embedded in a manuscript.
- Ingestion points: User-provided manuscript text or immunology research summaries.
- Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: None. The skill generates text-based evaluations only.
- Sanitization: Not applicable given the lack of executable capabilities.
Audit Metadata