internal-comms

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill is entirely documentation-based and contains no executable Python, JavaScript, or shell scripts.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its data processing requirements.
  • Ingestion points: Files examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md direct the agent to process content from Slack, Google Drive, Email, and Calendar.
  • Boundary markers: The templates lack specific instructions or delimiters to isolate processed data from the agent's core logic.
  • Capability inventory: The skill facilitates the reading and summarization of internal enterprise communications.
  • Sanitization: There are no defined procedures for validating or filtering the content retrieved from internal platforms before it is used to generate outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:54 PM