deal-champion-mapping
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the processing of untrusted external data, creating a surface for indirect prompt injection attacks.
- Ingestion points: The 'Interview' and 'Workflow' sections of
SKILL.mdinstruct the agent to collect and analyze external data such as call notes, transcripts, and email activity. - Boundary markers: The instructions lack explicit requirements for the agent to use delimiters or ignore embedded instructions within the provided data sources.
- Capability inventory: The skill performs complex reasoning and text generation but does not invoke dangerous system capabilities such as shell execution, network exfiltration, or file system modifications in the context of the processed data.
- Sanitization: There are no provisions for sanitizing or validating the contents of the ingested transcripts and emails before they are processed by the agent.
Audit Metadata