proposal-review
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of high-level instructions for an AI agent to perform a specific cognitive task (proposal review). It does not include scripts, executables, or commands that interact with the system at a low level.
- [PROMPT_INJECTION]: The skill processes user-supplied documents, which represents an indirect prompt injection surface where a malicious document could attempt to subvert the review process.
- Ingestion points: The skill reads proposal files, specification documents, and design documents from the user-provided directory or file path.
- Boundary markers: There are no specific delimiters or ignore instructions defined to isolate the untrusted document content from the agent's instructions.
- Capability inventory: The skill's capabilities are limited to reading files and performing web research. It does not utilize shell execution, file-writing, or direct network communication tools that would allow for exploitation of this surface.
- Sanitization: No explicit sanitization or validation of the input document content is specified in the instructions.
Audit Metadata