seo-technical
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including raw HTML, rendered JavaScript output, and server access logs (Apache/Nginx). This creates a surface for indirect prompt injection where malicious instructions could be embedded in the audited content to influence agent behavior.
- Ingestion points: Raw HTML and rendered page content captured during audits, and server logs or crawler CSV exports imported via
import_seo_exports.py. - Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions within the ingested evidence.
- Capability inventory: The skill can execute local Python scripts (
import_seo_exports.py,validate_llms_txt.py,manage_markdown_site.py, etc.), read project configuration, and generate documentation. - Sanitization: There are no explicit requirements for sanitizing or escaping the untrusted content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute several local Python scripts located in the
<suite-root>/scripts/directory for data processing and validation. These scripts are invoked with arguments such as file paths and URLs, representing a dynamic execution pattern within the local project environment.
Audit Metadata