skills/liangmiqwq/mo/global-projects/Gen Agent Trust Hub

global-projects

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local CLI tools (mo, mo-get-root) to manage projects, including listing, cloning, and initializing repositories.
  • [SAFE]: The skill accesses a local configuration file at ~/.config/morc.json to determine the user's project root directory; this is standard behavior for the tool's operation.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. Ingestion points: Reads project list from mo list and configuration from ~/.config/morc.json in SKILL.md. Boundary markers: None. Capability inventory: Executes shell commands (mo suite) and file operations on resolved paths in SKILL.md. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:46 AM
Security Audit — agent-trust-hub — global-projects