zapier-integration-helper

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code Detected] (SAFE): The skill consists entirely of a markdown file (SKILL.md) providing natural language instructions and metadata. No Python scripts, Node.js files, or Shell scripts are included.
  • [Category 8] Indirect Prompt Injection (LOW): The skill identifies itself as a helper for business automation, which involves processing external data.
  • Ingestion points: Processes user-provided descriptions of Zapier workflows, email contents, and spreadsheet data.
  • Boundary markers (absent): No specific delimiters or safety instructions are provided to the agent to distinguish between user instructions and data content.
  • Capability inventory: The skill metadata requests access to Read, Write, Edit, and Bash tools.
  • Sanitization (absent): No sanitization or validation logic is described in the prompt to handle potentially malicious instructions embedded in automation data.
  • [Category 7] Metadata Poisoning (SAFE): The metadata fields (name, author, description) are descriptive and consistent with the skill's stated purpose without containing hidden instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM