write-a-skill
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of agent instructions (SKILL.md) based on user-supplied requirements, which represents a surface for instruction-based attacks. * Ingestion points: User requirements and workflow triggers gathered during the drafting process. * Boundary markers: The process includes a manual review phase (Phase 3) to ensure instructions are clear and boundaries prevent misuse. * Capability inventory: The skill uses 'Write', 'Edit', and 'Bash' tools for file operations. * Sanitization: No automated sanitization of user-provided content is defined in the workflow.
Audit Metadata