skill-creator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local shell commands via Python scripts to initialize and package files.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a template generator that processes user input to create new instructions, which is a common surface for prompt injection.
- Ingestion points: User examples and reference materials gathered in Step 1 and Step 4.
- Boundary markers: The skill does not define specific markers to isolate user content in generated files.
- Capability inventory: The workflow includes shell script execution and file system access.
- Sanitization: No explicit sanitization or escaping of user input is mentioned.
- [DYNAMIC_EXECUTION]: The skill relies on executing local Python scripts to automate directory setup and validation.
Audit Metadata