documentation
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Step 5 of the skill instructions involves executing code examples found in documentation files. This creates a potential for arbitrary command execution if the documentation content is modified to include malicious code.
- [PROMPT_INJECTION]: The skill processes Markdown documentation as untrusted data, exposing a surface for indirect prompt injection. (1) Ingestion points: Markdown files throughout the repository. (2) Boundary markers: Absent. (3) Capability inventory: File system writes, doc generator execution, and example code execution. (4) Sanitization: None.
Audit Metadata