skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local script (scripts/validate-metadata.py) to validate metadata, which is a legitimate part of the skill's authoring workflow and represents intended vendor functionality.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface (Category 8) where user-provided metadata is interpolated into a shell command. Ingestion points: Metadata placeholders name and description within SKILL.md. Boundary markers: The command template employs double quotes to encapsulate inputs. Capability inventory: Execution of a bundled Python script via a subprocess. Sanitization: There is no explicit sanitization or escaping of the input strings performed within the skill instructions before they are passed to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 05:42 AM