The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The skill requires the Bash tool to execute Python scripts (e.g., scripts/generate_diagram.py, scripts/generate_report.py) which were referenced but not provided for analysis. This grants the agent the ability to execute code on the local system to generate visual assets.
[PROMPT_INJECTION] (LOW): (Category 8: Indirect Prompt Injection) The skill ingests untrusted user data to populate diagrams and reports, presenting a potential injection surface. 1. Ingestion points: Phase 1 (Problem Definition) and Phase 3 (Cause Brainstorming) in SKILL.md. 2. Boundary markers: None identified in the workflow for separating user input from script execution parameters. 3. Capability inventory: Bash execution of Python scripts as described in HOW_TO_USE.md. 4. Sanitization: No sanitization or validation of user-provided strings is documented before they are passed to the SVG/HTML generation scripts, which could lead to XSS or injection in generated documents.

fishbone-diagram