agency-ad-creative-strategist
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external, untrusted data during competitor research and analysis.
- Ingestion points: The strategist is instructed to perform 'Competitor ad library research' and 'messaging gap identification' as described in
SKILL.md. - Boundary markers: The instructions do not provide delimiters or specific guidelines for the agent to distinguish between trusted instructions and untrusted data found in external ad copy.
- Capability inventory: The skill is designed to work with Google Ads API integrations to pull performance data and deploy new ad variations as stated in the 'Tooling & Automation' section of
SKILL.md. - Sanitization: There are no requirements or mechanisms specified for sanitizing or filtering content retrieved from external ad libraries.
Audit Metadata