internal-comms

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its reliance on processing data from potentially untrusted or attacker-controllable sources.
  • Ingestion points: The instructions in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md direct the agent to read and summarize content from Slack messages, Google Drive documents, corporate emails, and external press releases.
  • Boundary markers: The guidelines lack explicit delimiters or instructions for the agent to treat ingested data as untrusted or to ignore embedded instructions.
  • Capability inventory: The prompts encourage the agent to use environment tools for Slack, Google Drive, Email, and Calendar access.
  • Sanitization: There are no requirements or instructions to sanitize or validate the content retrieved from these external sources before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:31 PM