channel-audit

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Data Analysis Scope: The skill accesses Microsoft Teams channel metadata and summaries of recent messages to calculate engagement metrics. This data is used to provide visibility into channel activity levels and is handled within the agent's session context.
  • Indirect Prompt Injection Surface: The skill ingests content from Teams channel messages to assess activity. While there is a potential for instructions embedded in messages to attempt to influence the agent's summary, the risk is considered low because the skill focuses on metadata extraction and structured report generation.
  • Tool Integration: The audit relies on the local workiq-ask tool to interact with the Teams environment. No evidence of unauthorized network operations, data exfiltration, or persistence mechanisms was detected in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 01:28 PM