skill-meta
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows standard delegation patterns for internal agent workflows and does not contain any malicious code or unsafe operations.- [COMMAND_EXECUTION]: The skill utilizes the Bash tool for parsing user arguments to determine the execution mode (interactive, analyze, or prompt). The bash script is restricted to basic control flow for argument handling.- [PROMPT_INJECTION]: Instructional markers like 'CRITICAL' and 'IMPORTANT' are used to ensure the agent correctly selects the 'Task' tool over the 'Skill' tool for subagent delegation, serving as functional guidance rather than a bypass of safety protocols.
Audit Metadata