etsy-product-detail

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external Etsy listing pages which could contain hidden instructions for the agent.
  • Ingestion points: The script scripts/extract-detail.py ingests untrusted content including document.body.innerText, listing titles, and product descriptions.
  • Boundary markers: There are no safety delimiters or instructions provided to the agent to ignore potentially malicious content embedded in the scraped data.
  • Capability inventory: The agent possesses the bash tool (as indicated by the eval pattern) and file system access to write results.
  • Sanitization: The data is trimmed of whitespace, but no specific sanitization is performed to remove or neutralize embedded natural language instructions.
  • [COMMAND_EXECUTION]: The skill uses the eval "$(python scripts/extract-detail.py ...)" pattern to generate and execute JavaScript code in the browser. While the specific script provided sanitizes input by mapping arguments to boolean values, the use of shell evaluation for dynamic code generation is a pattern that increases the attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 05:53 AM
Security Audit — agent-trust-hub — etsy-product-detail