skill-writing
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill functions as a meta-tooling package for agent skill development. Thorough analysis revealed no evidence of malicious patterns, obfuscation, unauthorized exfiltration, or persistence mechanisms.\n- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for processing user-supplied data to generate new agent instructions.\n
- Ingestion points: User-provided triggers and problem statements in
SKILL.md.\n - Boundary markers: The instructions mandate drafting explicit contracts and safety limits for new skills to prevent accidental behavior.\n
- Capability inventory: Python scripts (
init_skill.py,package_skill.py) provide file and directory management capabilities.\n - Sanitization: None; the skill relies on the agent's ability to interpret and formalize documentation following structured templates.\n- [COMMAND_EXECUTION]: The package includes local Python scripts to automate repetitive development tasks. These scripts perform standard file system operations within the local workspace and do not interact with remote resources or execute untrusted code.
Audit Metadata