seo-content
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and analyzes content from user-provided URLs, which introduces a surface for indirect prompt injection.
- Ingestion points: The skill accepts a URL as an input argument in SKILL.md.
- Boundary markers: No specific delimiters are defined to isolate the external content.
- Capability inventory: The skill can call external SEO tools and perform local file writes.
- Sanitization: No explicit content sanitization is described.
- [DATA_EXFILTRATION]: The skill accesses a local directory named .seo-cache to store and retrieve audit data.
- Evidence: It reads site-meta.json and audit-scores.json to maintain context between sessions.
- Findings: This file access is restricted to the skill's own cache and the skill recommends adding the directory to .gitignore.
- [COMMAND_EXECUTION]: The skill relies on DataForSEO MCP tools for data retrieval.
- Evidence: It calls tools such as kw_data_google_ads_search_volume and dataforseo_labs_bulk_keyword_difficulty.
Audit Metadata