call-recording-analyzer-skill
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external call transcripts and AI summaries from Clari via
clari_get_callandclari_get_call_summary. This represents an ingestion point for untrusted data that could contain malicious instructions designed to influence the agent's behavior during analysis or report generation. - Evidence:
- Ingestion points: Data is pulled from
clari_get_call(transcript) andclari_get_call_summaryin Stage 1a. - Boundary markers: The workflow lacks explicit delimiters (e.g., XML tags or Markdown blocks with warnings) to isolate transcript content from the analysis instructions.
- Capability inventory: The agent has the ability to write to CRM records (
hubspot_create_contact_note) and create email drafts (create_draft). - Sanitization: There are no instructions for sanitizing or escaping the transcript text before it is analyzed or included in the final HTML scorecard and Gmail draft.
Audit Metadata