copywriting

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from users during the context-gathering phase, which could potentially contain malicious instructions aimed at exploiting its execution capabilities.
  • Ingestion points: User-provided information in Phase 1 (Page Purpose, Audience, Product/Offer, Context) within SKILL.md is processed by the agent to generate copy.
  • Boundary markers: The instructions lack explicit boundary markers or delimiters to separate user-provided context from the agent's internal instructions, increasing the risk of the agent following instructions embedded within the data.
  • Capability inventory: The agent is instructed to use the ExecutionProxy Interface (e.g., rtk npm test) for terminal actions and sequentialthinking / context7 MCP loops as described in the Global Protocols section of SKILL.md.
  • Sanitization: There is no mention of sanitizing or validating the input provided by the user before it is used to influence the copywriting output or tool execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:35 AM
Security Audit — agent-trust-hub — copywriting