campaign-architect

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill recognizes the risk of malicious instructions within processed data (such as CSV exports) and includes a mandatory instruction to treat all input as untrusted and ignore embedded commands.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: Operations are restricted to local data processing and saving results to a specific memory path. No suspicious network activity or sensitive data access was found.
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill only references well-known official tools and transparency libraries from trusted vendors.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:29 PM
Security Audit — agent-trust-hub — campaign-architect