ctr-snippet-batch-optimize
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (GSC exports, SEO reports) and uses it to modify the project's source code, creating a surface for indirect prompt injection.
- Ingestion points: External GSC Performance exports and the
seo-work-brief.mdfile located at the site project root. - Boundary markers: Absent. The instructions do not define delimiters or provide specific directives for the agent to ignore potentially malicious instructions embedded within the SEO data reports.
- Capability inventory: The agent is authorized to read and modify files throughout the site codebase (e.g., React, Vue, Blade templates) to update metadata and schema.
- Sanitization: Absent. The skill lacks validation steps to ensure that data from the reports does not contain executable instructions or malicious content before it is interpolated into the code-writing process.
Audit Metadata