05-ad-copy-global

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for Indirect Prompt Injection (Category 8) by ingesting data from external context files to influence its behavior.
  • Ingestion points: The skill reads content from .agents/product-marketing-context.md and .agents/personal-brand-context.md (SKILL.md).
  • Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore any embedded commands within these context files.
  • Capability inventory: The skill is limited to text generation. No dangerous capabilities such as subprocess execution, file-writing, or network operations were found in the provided file.
  • Sanitization: There is no evidence of sanitization or validation of the content read from the context files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 08:12 AM
Security Audit — agent-trust-hub — 05-ad-copy-global