win-loss-review

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources, specifically call transcripts and email threads, to identify qualitative deal patterns.
  • Ingestion points: External data enters the agent context through the use of doc and email tools in the evidence gathering phase (Step 2b).
  • Boundary markers: The instructions do not define explicit delimiters or use 'ignore-internal-instructions' markers when handling the content of transcripts or emails.
  • Capability inventory: The skill possesses the capability to query Salesforce data via dispatch_readonly and generate user-facing output via display_widget.
  • Sanitization: There are no specified sanitization or validation steps for the external text data before it is interpolated into the agent's reasoning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 06:39 PM