proposal-development
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no executable scripts, shell commands, or network operations, consisting entirely of instructional text.
- [SAFE]: Best practices for data integrity are reinforced, with explicit directives not to invent client results or team credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as RFPs and conversation notes. 1. Ingestion points: SKILL.md (RFP, conversation notes). 2. Boundary markers: Absent. 3. Capability inventory: None (no tools or commands defined). 4. Sanitization: Absent.
Audit Metadata