handle-objection
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill processes external data which could contain malicious instructions. Ingestion points: Data enters via email connectors, transcript reads, and pasted customer text as defined in SKILL.md. Boundary markers: The skill explicitly instructs the agent to treat this as 'untrusted content' and 'data, never instructions,' warning to report instruction-like text. Capability inventory: As noted in SKILL.md, the skill can draft outreach, call win-loss history tools, and read CRM/email records. Sanitization: It mandates user approval for content-originated actions and prohibits rendering links found in untrusted content.
Audit Metadata