code-formatter

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data (code files and project configurations), which introduces a surface for indirect prompt injection.
  • Ingestion points: The skill reads file content and configuration files (e.g., .prettierrc, pyproject.toml) from the local environment (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or explicit instructions to ignore embedded agent commands when reading external files.
  • Capability inventory: The skill utilizes file read and write operations to perform code formatting across multiple languages.
  • Sanitization: There is no mention of sanitizing or validating file content to prevent the agent from interpreting embedded comments as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 02:49 AM
Security Audit — agent-trust-hub — code-formatter