internal-comms
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize large volumes of data from external and multi-user sources, creating a surface for indirect prompt injection attacks.
- Ingestion points: The files examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md instruct the agent to retrieve data from Slack messages, Google Drive documents, Emails, Calendar events, and External press articles.
- Boundary markers: The instructions do not define any delimiters or provide guidance to the agent to ignore instructions embedded within the retrieved data.
- Capability inventory: The agent has the capability to read sensitive internal communications and documents across multiple platforms to generate summaries and newsletters.
- Sanitization: There are no instructions for validating, filtering, or escaping content retrieved from external sources before it is processed or included in the output.
Audit Metadata