internal-comms
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown files and a license text, with no executable scripts, binaries, or active code components.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it instructs the agent to ingest and summarize data from Slack, Google Drive, Email, and Calendar without providing boundary markers or instructions to ignore embedded commands. 1. Ingestion points: Slack messages, emails, Google Drive documents, and Calendar events. 2. Boundary markers: Absent. 3. Capability inventory: The agent generates textual summaries and newsletters based on sourced content. 4. Sanitization: No content validation or sanitization is specified for the external data sources.
Audit Metadata