pipeline
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external CRM systems or user-provided exports, specifically including a 'notes or context' field. This creates an attack surface where malicious instructions could be embedded in the source data to influence the agent's reporting or risk assessment.
- Ingestion points: The skill pulls data through the Model Context Protocol (MCP) or accepts pasted exports containing deal notes.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the CRM notes.
- Capability inventory: The skill is primarily instructional and focused on generating a text-based pipeline report; it does not include scripts for file system modification, shell command execution, or network exfiltration.
- Sanitization: There is no evidence of sanitization for the content processed from the 'notes or context' fields.
Audit Metadata