linkfox-etsy-category-search

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill retrieves Etsy category information from an external vendor API (https://tool-gateway.linkfox.com), creating a potential surface for indirect prompt injection. * Ingestion points: scripts/etsy_category_search.py retrieves external category names via call_api. * Boundary markers: No delimiters or specific instructions are provided to the agent to treat category data as untrusted content. * Capability inventory: The skill scripts have permissions to write to the linkfox/ directory and perform network requests to vendor domains. * Sanitization: The ingested data is parsed as JSON, but there is no validation or filtering of string content to prevent prompt injection.
  • [COMMAND_EXECUTION]: The onboarding documentation instructs the user to manually execute shell commands for environment variable configuration and script execution. These actions are for troubleshooting and utilize legitimate vendor-provided tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:03 AM
Security Audit — agent-trust-hub — linkfox-etsy-category-search