skills/lev-os/agents/lev-plan/Gen Agent Trust Hub

lev-plan

Warn

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of arbitrary shell commands specified in the fitness_functions YAML frontmatter of plan files located in .lev/pm/plans/. These commands are executed during the plan validation process.
  • [COMMAND_EXECUTION]: Employs standard shell commands such as cat, mv, ls, and grep to manage file creation and lifecycle transitions.
  • [PROMPT_INJECTION]: The skill processes markdown files from the repository which may contain malicious instructions, representing an indirect prompt injection surface.
  • Ingestion points: Files matching .lev/pm/plans/plan-*.md.
  • Boundary markers: Uses YAML frontmatter delimiters, but lacks explicit instructions to disregard malicious embedded content.
  • Capability inventory: Subprocess execution of shell commands (fitness functions) and file system manipulation (mv, cat).
  • Sanitization: No sanitization or verification of the shell command strings is performed before execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 16, 2026, 04:48 PM
Security Audit — agent-trust-hub — lev-plan