call-prep
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration techniques were detected. The skill's operations align with its stated purpose of preparing sales call briefs.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted data from external sources.
- Ingestion points: Web search results (Step 2), LinkedIn profiles, email threads, and chat messages (Step 1) described in SKILL.md.
- Boundary markers: None specified in the execution flow to delimit untrusted content from system instructions.
- Capability inventory: Data retrieval from integrated CRM, Email, Chat, Transcripts, and Calendar; Web Search functionality.
- Sanitization: No explicit sanitization or validation of external content is described in the synthesis logic.
Audit Metadata