internal-comms
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from user-controllable external sources, creating a risk that malicious instructions could be processed and followed by the agent.
- Ingestion points: The instructions guide the agent to read Slack messages, Google Drive documents, emails, and calendar events to synthesize 3P updates, newsletters, and FAQs (found in
examples/3p-updates.md,examples/company-newsletter.md, andexamples/faq-answers.md). - Boundary markers: The skill fails to define clear delimiters or provide instructions to help the agent distinguish between data to be summarized and instructions hidden within that data.
- Capability inventory: The skill utilizes the agent's integrated access to sensitive communication tools and document repositories.
- Sanitization: No strategies for sanitizing, escaping, or validating external content are provided in the skill instructions.
Audit Metadata