copywriting

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use web search tools to perform competitor research and analyze customer sentiment on external sites such as Trustpilot.fr and Avis Vérifiés. This is a functional requirement for high-quality copywriting and does not involve downloading untrusted executable code.
  • [COMMAND_EXECUTION]: The SEO copywriting module mentions a local Python script, link_cluster_validator.py, which is used to validate internal linking structures. The skill suggests the agent run this script if it is present in the local environment, which is a standard procedure for development-oriented agent tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from the web (such as competitor landing pages and customer reviews) to inform the copywriting process. While it does not include explicit boundary markers to differentiate between instructions and data in these external sources, the risk is minimal as the agent's output is limited to text generation, and the skill's instructions focus on analysis rather than execution of found content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 04:47 PM
Security Audit — agent-trust-hub — copywriting