the-channel-guard

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily composed of instructional prompts for designing marketing campaigns. It calculates character limits for different encodings (GSM-7 vs Unicode) and ensures compliance requirements are met based on region.
  • [DATA_EXPOSURE]: The skill accesses local files such as .agents/product-context.md and references/sms-push-compliance.md. These are standard workspace files used to provide context for the agent and do not involve sensitive system paths or credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local context files and user inputs to generate campaign copy. Although it does not explicitly define boundary markers to separate untrusted data from instructions, the skill's actions are restricted to text generation and formatting, with no access to dangerous tools like shell execution or file-writing capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 12:19 PM