summarize-conversation-transcript

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill interacts exclusively with official Salesforce API endpoints, such as the REST Query API (/services/data/v63.0/query) and the Actions API (/services/data/v64.0/actions/standard/getConversationTranscript), which is consistent with its stated purpose.
  • [SAFE]: The instructions include robust privacy and safety constraints, specifically directing the agent to avoid repeating sensitive data like Social Security Numbers or credit card information that might appear in transcripts.
  • [SAFE]: The skill implements strict operational boundaries by prohibiting the agent from attempting to discover or guess API endpoints, requiring adherence to the paths explicitly defined in the skill documentation.
  • [SAFE]: The prompt engineering for the summarization task includes explicit 'grounding' instructions, requiring the agent to extract information only from the provided transcript and avoid inventing details.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 06:39 PM