carrier-relationship-management
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves the processing of potentially untrusted data from carriers, creating a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to analyze carrier bid packages, shipment data, and regulatory compliance records (SKILL.md).
- Boundary markers: The skill lacks instructions for using delimiters or boundary markers to distinguish untrusted data from the agent's core instructions (absent in SKILL.md).
- Capability inventory: The agent possesses the capability to make freight allocation decisions, negotiate rates, and initiate communications with carrier representatives, all of which could be manipulated by malicious data (SKILL.md, references/decision-frameworks.md).
- Sanitization: No sanitization or validation mechanisms are described for the ingestion of external data inputs (absent in SKILL.md).
Audit Metadata