gtm-sales-handoff
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions.
- Ingestion points: Discovery notes and call transcripts from CRM data are ingested in SKILL.md (Step 1 and Step 3).
- Boundary markers: The skill lacks explicit boundary markers or instructions for the agent to ignore embedded commands within the processed data.
- Capability inventory: The agent is instructed to query CRM systems and generate output artifacts in Markdown, HTML, or PDF formats.
- Sanitization: No evidence of input sanitization or filtering of external content was found.
Audit Metadata