copywriting

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user data, such as marketing briefs and copy samples, to generate its output. This creates a surface where malicious instructions hidden in the user content could influence the agent.
  • Ingestion points: User-provided inputs described as Situations A, B, and C, as well as writing samples provided for tone matching (SKILL.md).
  • Boundary markers: The skill lacks technical boundary markers or specific delimiters to isolate user-supplied copy from the system instructions.
  • Capability inventory: The skill possesses the capability to read local files for context, specifically targeting .agents/product-marketing.md and related context files (SKILL.md).
  • Sanitization: There is no evidence of filtering or escaping logic applied to the external user content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 08:07 PM