claap-sales-opportunity-detector

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a suite of Claap-specific MCP tools to manage its workflow.
  • Evidence: Commands include Claap:list_workspaces, Claap:get_recordings, Claap:get_recording_transcript, Claap:search_companies, and Claap:search_contacts to retrieve and enrich call data.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted data from external sources (meeting transcripts).
  • Ingestion points: Transcript data is fetched in Phase 2.3 via Claap:get_recording_transcript.
  • Boundary markers: The instructions lack explicit delimiters or safety headers to separate the transcript content from the analysis logic.
  • Capability inventory: The agent has the ability to browse organizational workspaces, list recordings, and search for company/contact details through the Claap MCP tools.
  • Sanitization: There is no evidence of filtering or sanitization of the transcript text before it is scored against the buying signal grid.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:21 PM
Security Audit — agent-trust-hub — claap-sales-opportunity-detector