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_functionsYAML 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, andgrepto 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