drafting-plans
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious instructions, obfuscation, or dangerous system commands were found. The skill is designed to guide the agent in drafting documentation and planning engineering tasks based on existing repository evidence.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository, creating a surface for indirect prompt injection. 1. Ingestion points: Reads existing plan documents in docs/plans/, code, schemas, and PR/issue context. 2. Boundary markers: No explicit delimiters are specified to separate ingested content from agent instructions. 3. Capability inventory: Filesystem read and write access restricted to documentation creation; no network or shell execution capabilities are utilized. 4. Sanitization: No specific sanitization or validation of the ingested repository content is performed.
Audit Metadata