product-frame
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from various untrusted external sources, creating a surface for indirect prompt injection.
- Ingestion points: The agent is directed to ingest and analyze content from the codebase, PRDs, support tickets, telemetry, customer quotes in CRM documents, and web search results as specified in SKILL.md and assets/research-depth.md.
- Boundary markers: The instructions do not define or require the use of specific delimiters to separate untrusted external content from the agent's core instructions.
- Capability inventory: The agent is expected to perform codebase inspections, execute repository queries, and perform SQL or API checks to validate claims as mentioned in assets/research-depth.md.
- Sanitization: No sanitization, filtering, or validation logic is specified for the external content before it is processed by the agent.
Audit Metadata