ads-budget

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external advertising performance data, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: Data is collected from active ad platforms (SKILL.md).\n
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts in the ingested data.\n
  • Capability inventory: The agent uses the data to generate internal reports and recommendations (BUDGET-STRATEGY-REPORT.md).\n
  • Sanitization: There are no documented procedures for sanitizing or validating campaign names, creative content, or other platform-provided strings.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:42 AM
Security Audit — agent-trust-hub — ads-budget