quality-score-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implementation follows standard patterns for data analysis. All external resources, including the
googleadsagent.aidomain and associated GitHub repositories, are consistent with the author's identity and stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection as it processes data from an external source (Google Ads API).
- Ingestion points: Data enters the context via the
keywordDatavariable inSKILL.md. - Boundary markers: The skill does not currently implement specific delimiters to separate untrusted data from instructions.
- Capability inventory: The logic is limited to internal data mapping and mathematical calculation; no dangerous capabilities such as shell command execution, file writing, or unauthorized network operations are present in the provided scripts.
- Sanitization: The skill generates descriptive analysis and text strategies, minimizing the risk of interpreted malicious content.
Audit Metadata