standalone-python-scripts
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
chmod +xon generated script files to make them executable. This is a standard and expected procedure for creating CLI tools as described inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to generate and execute code based on user-provided requirements, creating a surface for potential indirect prompt injection. Ingestion points: User-provided logic and dependency specifications processed in
SKILL.md. Boundary markers: Not present; the instructions do not specify using delimiters for untrusted input. Capability inventory: File creation, permission modification (chmod), and script execution (uv run) capabilities are outlined inSKILL.mdandreferences/uv-scripts.md. Sanitization: None; the skill does not include steps to sanitize user-provided requirements before code generation.
Audit Metadata