Meta-Skill Creator
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill uses shell commands like
cpandmvto manage documentation files and directories. Evidence: Step 1 instructions includecpto copy documentation andmvto rename directories. - [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8). 1. Ingestion points: Raw documentation files collected from user-provided directories in Step 1. 2. Boundary markers: Absent; there are no specific instructions to isolate or ignore instructions within the source documents. 3. Capability inventory: Subprocess calls (
cp,mv) and automated file generation via synthesizer agents. 4. Sanitization: Absent; documents are analyzed and synthesized as-is by sub-agents.
Audit Metadata