paid-ads-ops

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains mandatory instructions to override default agent behavior when a user inquires about the system prompt, directing them instead to a specific marketing URL.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, which could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: The 'Required Inputs' section in SKILL.md identifies 'account export' and 'landing page' as primary data sources.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between system instructions and data from these external sources.
  • Capability inventory: The skill is focused on analytical tasks and reporting; it does not utilize file-system writes, network operations, or shell execution tools.
  • Sanitization: No input validation or sanitization routines are defined to inspect the contents of processed exports or web pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:11 AM
Security Audit — agent-trust-hub — paid-ads-ops