zg-product-info-collector
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and summarize information from external documents, folders, and existing knowledge bases. This creates a potential surface for indirect prompt injection where malicious instructions embedded in source documents could attempt to influence the agent's behavior during the extraction process.
- Ingestion points: The skill reads content from folders, documents, and knowledge base paths (SKILL.md).
- Boundary markers: The instructions do not define explicit boundary markers or delimiters to isolate ingested content from the system prompt.
- Capability inventory: The skill has capabilities to read files and write new product cards or indices to the local environment (SKILL.md).
- Sanitization: The skill contains instructions for anonymizing sensitive personal data but lacks specific sanitization for control sequences or prompt injection payloads within external documents.
Audit Metadata