internal-comms

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): The skill exhibits a significant surface for indirect prompt injection (Category 8).
  • Ingestion points: The instructions in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md direct the agent to fetch and process data from Slack, Google Drive, Email, and Calendar.
  • Boundary markers: There are no boundary markers or 'ignore' instructions to prevent the agent from following malicious commands embedded within the retrieved messages or documents.
  • Capability inventory: The skill enables the agent to aggregate and relay potentially sensitive organizational data from various communication tools.
  • Sanitization: No sanitization or validation steps are defined for the content retrieved from these external sources.
  • NO_CODE (SAFE): The skill is composed exclusively of Markdown documentation and does not include any executable scripts, dependencies, or configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM