learning-leadership-development
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- [Dynamic Execution] (MEDIUM): The skill uses
sys.path.insert(0, str(framework_path))where the path is computed at runtime usingPath(__file__).parent.parent / "framework". This pattern of dynamic loading from computed paths can be exploited if the directory structure is manipulated to redirect imports to malicious modules.\n- [Indirect Prompt Injection] (LOW): The skill processes untrusted input through thecontentparameter, creating an injection surface.\n - Ingestion points:
parameters["content"]inskill.py.\n - Boundary markers: None present in the code or prompt logic.\n
- Capability inventory: None; the skill lacks network access, file write permissions, or shell execution capabilities in the provided snippet.\n
- Sanitization: None; the content is processed directly.\n- [General Code Issue] (INFO): The variable
skill_diris referenced in theexecutemethod for output strings and artifacts but is not defined anywhere in the script, which will result in aNameErrorduring execution.
Audit Metadata