internal-comms

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to pull data from external, non-static sources such as Slack posts, emails, and shared documents. This creates a vulnerability where instructions embedded in those sources by other users could influence the agent's output or behavior.
  • Ingestion points: Slack, Google Drive, Email, and Calendar as specified in the example files (e.g., examples/3p-updates.md).
  • Boundary markers: There are no instructions to the agent to distinguish between the content it is summarizing and potential instructions within that content.
  • Capability inventory: The skill utilizes read-access tools for collaboration platforms to gather context for reports.
  • Sanitization: The instructions do not include steps to sanitize or filter out malicious commands or formatting from the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:56 PM
Security Audit — agent-trust-hub — internal-comms