grant-compliance-checking
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill instructs the agent to read and analyze potentially untrusted external files to ensure compliance. * Ingestion points: Files in /grant/, /funding/, and /proposal/ directories, as well as grant*.md and proposal*.md files. * Boundary markers: None specified in the instructions to separate data from system instructions. * Capability inventory: The skill itself contains no executable code, tool definitions, or network capabilities. * Sanitization: No sanitization or content validation logic is defined.
- [No Code] (SAFE): The skill consists entirely of instructional markdown and metadata with no executable scripts or binary files.
Audit Metadata