brand-protection-shopify
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted marketplace data which creates a surface for indirect prompt injection. * Ingestion points: Customer reviews, product titles, and seller names processed in scripts/detector.py. * Boundary markers: Absent; the skill does not use specific delimiters or instructions to isolate external data. * Capability inventory: No dangerous capabilities, such as file system writes, network exfiltration, or subprocess execution, were identified in scripts/detector.py or scripts/templates.py. * Sanitization: The skill uses basic string normalization but lacks robust sanitization for instructions embedded in external marketplace content.
Audit Metadata