ab-test-store-listing
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No executable code, scripts, or automated tool configurations were detected within the skill. The instructions are purely advisory and qualitative in nature.\n- [INDIRECT_PROMPT_INJECTION]: The skill establishing a data ingestion point for processing external information.\n
- Ingestion points: The agent is instructed to read
app-marketing-context.mdfor background context during the initial assessment phase.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potential commands embedded within the context file.\n
- Capability inventory: The skill defines no tool access, network capabilities, or shell execution permissions, which effectively neutralizes the risk of automated exploitation from the ingested data.\n
- Sanitization: No validation or filtering mechanisms are defined for the external file content.
Audit Metadata