internal-comms

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
  • Ingestion points: As detailed in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md, the agent is directed to pull data from Slack, Google Drive, Email, and external press.
  • Boundary markers: Absent. No instructions are provided to use delimiters or to ignore instructions embedded within the source documents.
  • Capability inventory: The skill utilizes data retrieval tools and generates natural language summaries for internal distribution.
  • Sanitization: Absent. The instructions do not specify any validation or sanitization of the content retrieved from enterprise or web sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:09 PM
Security Audit — agent-trust-hub — internal-comms