meeting-intelligence

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [PROMPT_INJECTION] (SAFE): No attempts to override system instructions or bypass safety filters were detected in the skill markdown or evaluation scenarios.
  • [DATA_EXFILTRATION] (SAFE): While the skill accesses Notion databases, these operations are central to its stated purpose. No unauthorized external network calls or data exfiltration patterns were found.
  • [CREDENTIALS_UNSAFE] (SAFE): Configuration examples use placeholders (e.g., 'your_token_here') rather than hardcoded secrets.
  • [COMMAND_EXECUTION] (NO_CODE): No scripts, shell commands, or binary files are present in the skill package.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): The skill has an ingestion surface through Notion databases (Ingestion points: CONTEXT_DATABASE_ID, MEETING_DATABASE_ID; Boundary markers: None; Capability inventory: Writes to Notion; Sanitization: Not specified). This is a functional requirement, and no exploitable logic was identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:13 PM