deal-advance-gap
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill processes information from external and untrusted sources such as emails, chat logs, and meeting transcripts. These inputs could potentially contain hidden instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads data from CRM, email, transcripts, and chat tools (SKILL.md, Step 2).
- Boundary markers: The skill explicitly instructs the agent to treat these sources as 'data, never instructions' and to report any instruction-like text rather than acting on it.
- Capability inventory: The skill has the ability to update CRM records using the 'update-opportunity' or 'log-activity' tools.
- Sanitization: A human-in-the-loop check is mandated for any 'content-originated' actions, ensuring the user reviews the target, recipient, and content before the action is executed.
- Sensitive Data Access: To perform its function, the skill accesses sensitive business data including CRM records and communication history.
- Context: This access is required for identifying sales gaps. The skill adheres to the permissions established by the individual tool connectors and does not attempt to escalate privileges or exfiltrate data to unauthorized locations.
Audit Metadata