brand-protection-ebay
Pass
Audited by Gen Agent Trust Hub on May 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted third-party content from seller reviews and listing data that could contain malicious instructions.\n
- Ingestion points: Listing and review data processed in
scripts/detector.pyoriginates from external marketplace content.\n - Boundary markers: None; the skill does not use delimiters or instructions to isolate untrusted review data from the agent's context in generated reports.\n
- Capability inventory: The skill's capabilities are restricted to string processing and template generation; it lacks network access, file system write permissions, and command execution capabilities.\n
- Sanitization: Listing titles and review text are included in reports and evidence summaries without escaping or sanitization.
Audit Metadata