quality-score-breakdown

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The analyzed file contains descriptive text and metadata explaining the skill's purpose but lacks any executable code, shell commands, or programmatic instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill's documentation describes processing external data from Google Ads, such as keyword lists and landing page content, which represents a potential surface for indirect prompt injection. However, no logic for data ingestion or processing is implemented in the provided file.
  • Ingestion points: External Google Ads metrics and ad copy (mentioned in SKILL.md).
  • Boundary markers: None present.
  • Capability inventory: No tools or scripts are defined.
  • Sanitization: No data validation or sanitization logic is provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 05:56 AM
Security Audit — agent-trust-hub — quality-score-breakdown