diagramming-expert
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Extensive review of all five files confirms that the content is limited to instructional documentation and character references. No malicious code, data exfiltration patterns, or persistence mechanisms were detected.
- [PROMPT_INJECTION]: An indirect prompt injection surface is noted as a result of the skill's core functionality. 1. Ingestion points: The skill processes user-supplied technical or psychological concepts to generate diagrams (SKILL.md). 2. Boundary markers: There are no explicit delimiters used to isolate input data from the skill's primary instructions. 3. Capability inventory: The skill utilizes 'Read', 'Write', and 'Edit' tools to interact with the file system for document creation. 4. Sanitization: No input validation or filtering is specified for the content provided by the user. This surface is assessed as safe as it is intrinsic to the skill's intended purpose of document transformation.
Audit Metadata