skills/agricidaniel/claude-seo/seo/Gen Agent Trust Hub

seo

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with various well-known APIs to fetch SEO and maps data. Evidence includes curl commands to Google PageSpeed Insights, Moz API, Bing Webmaster, DataForSEO, Geoapify, and OpenStreetMap (Overpass API) endpoints.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts and CLI tools to perform its logic. Evidence: calls to scripts/google_auth.py, scripts/google_report.py, and npx lighthouse for technical audits.
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified due to processing external website content. Ingestion points: Content from user-provided URLs is ingested in commands such as /seo audit and /seo page via fetch_page.py and parse_html.py. Boundary markers: No explicit delimitation or instructions to ignore embedded prompts are provided in the skill instructions. Capability inventory: The skill has capabilities to execute Python scripts, perform network requests, and generate complex reports. Sanitization: There is no evidence of sanitization or filtering of external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 03:09 AM