internal-comms

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to ingest and summarize data from untrusted internal sources, creating a surface for indirect prompt injection.
  • Ingestion points: Content is retrieved from Slack, Google Drive, Email, and Calendars as defined in guideline files like examples/3p-updates.md and examples/faq-answers.md.
  • Boundary markers: There are no instructions for the agent to use delimiters or 'ignore embedded instructions' warnings when processing this external content.
  • Capability inventory: The skill utilizes tools to read communications and then produces formatted summaries based on that data.
  • Sanitization: The instructions do not include any methods for escaping, validating, or filtering the retrieved information before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 09:45 AM