internal-comms
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it directs the agent to ingest data from untrusted sources such as Slack messages, emails, shared documents, and external press articles without boundary markers or sanitization instructions. Ingestion points: examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md. Boundary markers: Absent. Capability inventory: Content summarization and output generation using platform-integrated tools (Slack, Email, Google Drive, Calendar). Sanitization: Absent.
- [NO_CODE]: No executable scripts or code files were found; the skill consists entirely of markdown guidelines and instructions.
Audit Metadata