post-meeting-execution
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted meeting data, creating a surface for indirect prompt injection. Ingestion points: Meeting transcripts and attendee details from the
{{MEETING_NOTES_TOOL}}placeholder are loaded into the agent's context in Step 1. Boundary markers: The instructions do not employ technical delimiters (such as XML tags) or specific directives to isolate untrusted transcript data from the skill's logic. Capability inventory: The skill can write to the CRM, update account memory, post to Slack, and initiate LinkedIn connection requests. Sanitization: No validation or escaping of the meeting transcript is performed before the data is used to influence agent decisions and outputs.
Audit Metadata