etsy-category-listing

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation instructs the agent to use a dynamic execution pattern: eval "$(python scripts/extract-listings.py)". This involves the shell evaluation of code generated by a script at runtime, which is a recognized risk vector for command injection.
  • [PROMPT_INJECTION]: The skill processes untrusted data from Etsy listing pages, creating a vulnerability to indirect prompt injection.
  • Ingestion points: Untrusted product data is ingested from Etsy category and subcategory pages during extraction (scripts/extract-listings.py).
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are used to wrap the extracted data.
  • Capability inventory: The skill has the capability to navigate URLs, execute Javascript in the browser, and perform file operations via the browser-act tool.
  • Sanitization: The skill does not perform any sanitization or validation of the extracted string fields (like titles or shop names) before providing them to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 05:53 AM
Security Audit — agent-trust-hub — etsy-category-listing