creating-skills
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): Analysis of the markdown content reveals no prompt injections, hardcoded credentials, or malicious command execution patterns. All referenced scripts (e.g., init_skill.py) are described as part of a local development workflow for skill creation.
- Indirect Prompt Injection (SAFE): The skill defines a workflow for processing user examples into logic, which is a standard developer documentation use case.
- Ingestion points: User-provided usage examples in the 'Understanding' phase.
- Boundary markers: None specified in the instructional text.
- Capability inventory: The guide describes a process for creating Python/Bash scripts and performing file system operations.
- Sanitization: Not addressed in the instructions.
Audit Metadata