internal-comms

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of processing untrusted external data.
  • Ingestion points: The skill explicitly instructs the agent to gather content from Slack posts, emails, Google Drive documents, and external press articles as seen in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md.
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are present to protect the prompt context when interpolating external data.
  • Capability inventory: The skill utilizes read capabilities for communication and document tools. While no high-risk execution tools (like shell access) are explicitly invoked in the skill files, the ingested content directly shapes the agent's output.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 01:10 PM
Security Audit — agent-trust-hub — internal-comms