etsy-tony-competitor

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Etsy product pages and user-provided files, which is a known attack surface for indirect prompt injection. Ingestion points: Public Etsy product pages, screenshots, and user-organized documents analyzed in SKILL.md. Boundary markers: The skill instructs the agent to record the source link or filename and the date for every piece of information extracted, establishing a clear attribution chain. Capability inventory: The skill's instructions are limited to reading and comparing public content using browser tools; it does not request capabilities for filesystem writes or network exfiltration. Sanitization: Instructions mandate distinguishing between observable data and inferences, and explicitly prohibit bypassing logins or CAPTCHAs, which helps mitigate the impact of instructions embedded in the analyzed content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:20 AM
Security Audit — agent-trust-hub — etsy-tony-competitor