internal-comms

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from potentially untrusted external sources (Slack, Google Drive, Email, and Calendar) to generate its outputs.\n
  • Ingestion points: Instructions in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md direct the agent to gather context from Slack messages, Google Drive documents, emails, and calendar events.\n
  • Boundary markers: There are no boundary markers or explicit instructions to treat the fetched content purely as data, leaving the agent vulnerable to instructions embedded within those sources.\n
  • Capability inventory: The skill utilizes the agent's broad access to corporate communication and productivity tools to aggregate information.\n
  • Sanitization: No sanitization, filtering, or verification of the integrity of the external data is performed before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 03:16 PM
Security Audit — agent-trust-hub — internal-comms