use-skill-craft
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill's functionality is limited to providing structural guidance for instruction authoring and does not perform sensitive operations or access remote resources.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to review and modify external instruction files. This is inherent to the skill's purpose and is assessed as safe in this context.
- Ingestion points: The skill analyzes content from files specified in user arguments, such as AGENTS.md or skill files.
- Boundary markers: The instructions do not prescribe the use of delimiters or specific ignore-directives when processing ingested content.
- Capability inventory: The skill is intended to facilitate reading, reviewing, and writing local file content.
- Sanitization: No explicit sanitization or filtering of the content within the ingested files is implemented.
Audit Metadata