internal-comms-anthropic

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from Slack, Email, and Google Drive to generate internal communications, which could allow malicious instructions embedded in those sources to influence the agent's behavior.\n
  • Ingestion points: examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md specifically instruct the agent to gather and summarize data from communication channels.\n
  • Boundary markers: There are no explicit delimiters or instructions to ignore or isolate embedded instructions within the source data.\n
  • Capability inventory: The skill leverages the agent's primary capabilities to read messages, emails, and shared documents across a workspace.\n
  • Sanitization: The skill does not provide instructions for validating or sanitizing the content retrieved from these external tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 09:45 PM
Security Audit — agent-trust-hub — internal-comms-anthropic