goal-instruction-writer
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill package consists entirely of markdown instructions and reference documentation. There are no executable scripts, shell commands, or binaries included.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input for auditing and drafting instructions. 1. Ingestion points: User requests to draft, refine, or audit goals in SKILL.md. 2. Boundary markers: The skill instructs the agent to return the results within markdown fenced blocks. 3. Capability inventory: The skill itself has no capabilities for file system access, network communication, or code execution. 4. Sanitization: The 'Audit' mode specifically directs the agent to identify and propose fixes for 'unsafe or unauthorized transitions' in the provided input data.
Audit Metadata