visualize-code
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from local source files, which creates a surface for indirect prompt injection where instructions embedded in code comments or strings could influence the agent. 1. Ingestion points: Local source files at the user-provided path (SKILL.md). 2. Boundary markers: Absent; there are no specific instructions to ignore embedded instructions within the files. 3. Capability inventory: File discovery (Glob), file reading, and Mermaid diagram generation (SKILL.md). 4. Sanitization: Absent; no specific filtering or validation of the ingested code content is mentioned.
- [DATA_EXFILTRATION]: The skill accesses and reads source code files from the local file system. This access is restricted to the path provided by the user and is essential for generating the requested diagrams.
Audit Metadata