PPC Campaign Strategist
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from untrusted external sources, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: Data enters the agent context via
WebSearch,WebFetch, and Google Ads API integrations as described in the Core Capabilities and Tooling sections ofSKILL.md. - Boundary markers: The instructions do not specify delimiters or warnings to ignore instructions embedded within the ingested external content.
- Capability inventory: The skill requests and describes the use of
Bash,Write, andEdittools, which provides a significant capability set if the agent is manipulated by external data. - Sanitization: The skill lacks instructions for validating or sanitizing retrieved content before it is used for automation or strategy generation.
Audit Metadata