writer-skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Prompt Injection] (LOW): The skill is susceptible to Indirect Prompt Injection. It ingests untrusted data (user-provided templates) and uses that data to generate new skill files.
  • Ingestion points: Template text or file paths provided by the user in '模板来源'.
  • Boundary markers: None. The instructions do not define delimiters to separate user data from system instructions.
  • Capability inventory: The agent has the capability to write files (SKILL.md, structure.yaml, requirements.yaml) into the backend/data/skills/ directory.
  • Sanitization: None. There are no instructions to sanitize the content of the generated files or the skill-id used for the directory name.
  • [Command Execution] (LOW): The skill directs the agent to perform filesystem write operations. Without strict sandboxing or path validation, this could be abused for path traversal (e.g., using ../../ in the skill-id) to overwrite existing configuration or system files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM