meeting-briefing
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is comprised entirely of markdown-based instructions and briefing templates. No malicious instructions, obfuscation, or safety bypasses were detected.\n- [NO_CODE]: No script files, executables, or package dependency manifests are included in the skill.\n- [PROMPT_INJECTION]: The skill specifies a workflow that ingests external data from email and chat systems, which represents an indirect prompt injection surface. This is evaluated as safe because the skill does not possess any code or capabilities that could be maliciously triggered.\n
- Ingestion points: Step 3 (Calendar, Email, Chat, Documents, CLM, CRM)\n
- Boundary markers: None; the templates do not define markers to separate untrusted content from briefing instructions.\n
- Capability inventory: None; the skill provides no code or tool execution logic.\n
- Sanitization: None; no validation or cleaning of external data is specified in the instructions.
Audit Metadata