skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to perform local file system operations, specifically creating directory structures for new skills using mkdir -p.
  • [PROMPT_INJECTION]: The skill is a generator that interpolates user-supplied data into a SKILL.md file, creating a risk of indirect prompt injection.
  • Ingestion points: Requirements gathered in 'Step 1: Gather Requirements' (Purpose, Triggers, Instructions) are used as content for the generated skill.
  • Boundary markers: No boundary markers or 'ignore' instructions are present in the provided templates to isolate user input from the generated instruction set.
  • Capability inventory: The skill uses Bash, Read, Write, Grep, and Glob to manage and validate the created files.
  • Sanitization: The skill lacks validation or sanitization mechanisms to ensure user-provided text does not contain malicious instructions that could compromise the agent when the generated skill is later activated.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 01:36 PM