paid-media-ppc-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted data from advertising APIs, which could be manipulated to include malicious instructions.
- Ingestion points: The skill instructions in
SKILL.mdexplicitly direct the agent to pull live account data, includingaccount_summary,list_campaigns, andauction_insightsfrom Google Ads, Microsoft Advertising, and Amazon Ads platforms. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potential commands embedded within the ad campaign data (e.g., in campaign names, ad copy, or keyword lists).
- Capability inventory: The agent is granted significant capabilities, including the ability to "Execute structural changes directly," such as creating campaigns, adjusting bid strategies, and reallocating budgets via API integrations mentioned in
SKILL.md. - Sanitization: There is no mention of sanitizing or validating the external data before it is processed by the LLM or used to trigger tool actions.
Audit Metadata