seo-quality-gates
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content drafts (SEO changes, HTML, JSON-LD) to identify policy violations. This ingestion represents a surface where an agent could be influenced by instructions hidden in the analyzed data.
- Ingestion points:
proposed_change,raw_html, andjson_ldinputs defined incontract.yaml. - Boundary markers: None explicitly defined, though the safety-oriented instructions provide a functional boundary.
- Capability inventory: Local analysis via
scripts/diff_gate.pyandscripts/lint.py. - Sanitization: None; the agent is instructed to perform semantic inspection for quality gates.
- [COMMAND_EXECUTION]: Provides Python scripts for the agent to locally analyze draft files and git diffs for risky SEO changes.
- [EXTERNAL_DOWNLOADS]: References official Google Search documentation for policy enforcement. These targets are well-known services and do not represent a security risk.
Audit Metadata