write-proposal
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (rough notes or descriptions) to generate proposals without using delimiters or instructions to ignore embedded commands.
- Ingestion points: User input provided for proposal drafting as described in SKILL.md.
- Boundary markers: No markers or clear separation provided between user content and agent instructions.
- Capability inventory: The skill uses file reading for templates and examples, while the underlying agent typically provides shell and filesystem access.
- Sanitization: No input validation or sanitization of user-provided notes is performed.
Audit Metadata