evidence-based-reviews
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze data from external, untrusted sources such as manufacturer websites, retailer review corpora, and owner forums (specified in SKILL.md under Required inputs). This processing of third-party content presents a surface for indirect prompt injection, where an adversary could embed malicious instructions in external content to manipulate the agent's output or behavior.
- Ingestion points: Manufacturer pages, retailer review corpora, owner forums, and expert publications.
- Boundary markers: The instructions lack specific boundary markers or delimiters to isolate untrusted content.
- Capability inventory: None. No subprocess, network, or file-write capabilities are defined in the skill.
- Sanitization: No sanitization or filtering logic is specified for the external data.
Audit Metadata