internal-comms

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection via the processing of untrusted external data.
  • Ingestion points: Slack, Google Drive, Email, and Calendar content (identified in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md).
  • Boundary markers: Absent; no instructions are provided to the agent to distinguish data from embedded instructions.
  • Capability inventory: The skill leverages tool access to corporate communication and document management systems.
  • Sanitization: Absent; no content validation is performed before summarization.
  • [NO_CODE]: The skill contains only documentation and instructional markdown files, with no associated executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 10:49 AM