seo-geo-factdensity

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external web pages.
  • Ingestion points: Processes rendered_dom and raw_html from external URLs fetched via the WebFetch tool.
  • Boundary markers: No specific boundary markers or delimiters for the ingested content are defined in the instructions.
  • Capability inventory: The skill can execute shell commands via Bash and run a local Node.js script (scripts/factdensity.mjs), though these are used for processing and reporting metrics.
  • Sanitization: The instructions emphasize manual review and deterministic counts, but do not specify sanitization for the raw HTML content.
  • [COMMAND_EXECUTION]: The skill documentation describes the use of a local Node.js script for reproduction of findings.
  • Evidence: The verification section references node scripts/factdensity.mjs --url <u> as the method for reproducing numeric counts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 08:09 PM
Security Audit — agent-trust-hub — seo-geo-factdensity