internal-comms

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill is susceptible to Indirect Prompt Injection due to its reliance on external data ingestion.
  • Ingestion points: examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md instruct the agent to pull data from Slack, Google Drive, Email, Calendar, and External Press.
  • Boundary markers: The skill lacks any instructions for the agent to use delimiters or ignore potentially malicious instructions embedded within the retrieved messages or documents.
  • Capability inventory: The agent has the capability to read across various sensitive enterprise communication channels and summarize them into new documents.
  • Sanitization: There is no instruction for the agent to sanitize, escape, or validate the content retrieved from untrusted sources (especially Slack and External Press) before including it in drafts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:31 PM