internal-comms
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Risk. The skill is designed to ingest data from external, potentially attacker-controlled sources such as Slack messages, Google Drive documents, and company emails to summarize updates and FAQs.
- Ingestion points: Processes content from Slack channels, Google Drive docs, and emails (defined in
examples/3p-updates.md,examples/company-newsletter.md, andexamples/faq-answers.md). - Boundary markers: The instructions lack explicit delimiters or 'ignore' instructions to prevent the model from obeying commands embedded within the fetched data.
- Capability inventory: The skill has read access to sensitive workspace data (Slack, Drive, Email, Calendar) and write capabilities (generating reports/comms that other employees will read).
- Sanitization: There is no evidence of content sanitization or validation of the fetched external data before it is interpolated into the final output.
Audit Metadata