diagram-reports-generator
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Command Execution (MEDIUM): The skill instructs the agent to install and run a Python script (diagram-report.py) bundled within the skill's resources. This involves local code execution on the user's filesystem to perform its primary function.
- Prompt Injection (LOW): The skill presents an indirect prompt injection surface (Category 8) by processing untrusted data.
- Ingestion points: The script parses content from 'docs/chapters/*/index.md' files.
- Boundary markers: No specific boundary markers or instruction-ignoring delimiters are defined for the parsing logic.
- Capability inventory: The skill possesses file system write access (to 'docs/learning-graph/') and the ability to execute Python subprocesses.
- Sanitization: There is no evidence of sanitization or validation of the text extracted from the markdown specifications before it is used in report generation.
Audit Metadata