paid-ads
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions facilitate the processing of untrusted external content, creating a surface for indirect prompt injection. \n
- Ingestion points: The agent is directed to gather campaign goals, product offers, and landing page URLs from the user (
SKILL.md). \n - Boundary markers: The provided instructions do not include explicit delimiters or warnings for the agent to ignore potentially malicious instructions embedded within user-provided context or external landing pages. \n
- Capability inventory: The skill integrates with tools for Google Ads, Meta Ads, and LinkedIn Ads, providing the agent with the ability to modify advertising platform configurations based on the processed input. \n
- Sanitization: There is no evidence of input validation or sanitization protocols for the external data collected during the discovery phase.
Audit Metadata