skill-converter
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior detected. The skill instructions focus on organizational and formatting tasks for agent definitions.
- [PROMPT_INJECTION]: The skill facilitates the processing of external upstream documents, which represents a surface for indirect prompt injection. (1) Ingestion points: The skill reads external agent specifications, role definitions, and prompt files. (2) Boundary markers: No explicit delimiters or ignore-instructions are specified for the source data. (3) Capability inventory: The skill writes to the local file system to create SKILL.md, README.md, and metadata files. (4) Sanitization: The workflow requires the agent to manually rewrite the source into a neutral core and remove extraneous narration, which serves as a procedural control.
- [DATA_EXPOSURE]: File system operations are confined to reading repository patterns and writing skill-related artifacts. This access is consistent with the skill's stated purpose as a conversion and packaging utility.
Audit Metadata