seo-local
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute specific Python scripts (
validate_seo_findings.py,manage_markdown_site.py,manage_markdown_work.py) to perform its primary functions of audit validation and document management. - [DYNAMIC_EXECUTION]: Executable paths for the skill's tools are determined at runtime by resolving a suite root directory through environment variables or local configuration files (
.seo-suite-runtime.json). - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as web page content and Google Business Profile reviews, which serves as a potential ingestion surface for indirect prompt injection.
- Ingestion points: Web pages, business profile data, and user reviews are collected during the audit process (documented in SKILL.md and references/local-evidence-protocol.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present for the external data being processed.
- Capability inventory: The skill can execute local Python scripts and write Markdown files to the local file system.
- Sanitization: The instructions do not specify any explicit filtering or sanitization of the external content before processing.
Audit Metadata