seo-page
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts and shell commands to parse URLs and query Google Search Console data (e.g.,
analyze_gsc.py,url_inspection.py). These operations are necessary for the skill's primary function of SEO auditing. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes untrusted third-party HTML content during its analysis phase.
- Ingestion points: Phase 1a and Phase 5 use
WebFetchto download HTML from user-provided target URLs and competitor pages (SKILL.md). - Boundary markers: The skill does not employ explicit delimiters or system instructions to the agent to disregard potential instructions embedded in the external content.
- Capability inventory: The skill has access to
bash,python3,WebFetch, andWebSearchtools (SKILL.md). - Sanitization: There is no evidence of HTML sanitization or filtering before the content is processed for SEO scoring.
- [DATA_EXFILTRATION]: The skill reads business context from a local JSON file located at
$HOME/.toprank/business-context/$DOMAIN.json. This is an application-specific configuration path and does not represent access to sensitive system credentials or private user data.
Audit Metadata