quality-score-fixer
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for read-only diagnostics of Google Ads performance. It includes explicit instructions to 'Change nothing' and 'Do not change bids, keywords, ads, or pages', ensuring it operates within a restricted, safe scope.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from ad copies and landing pages. However, the risk is minimal because the skill lacks capabilities to write files, execute commands, or perform network exfiltration.
- Ingestion points: Processes triggered queries, current ad assets, and landing page copy (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: The skill is restricted to read-only analysis and diagnostic reporting.
- Sanitization: Absent.
Audit Metadata