geo-content-optimizer

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local Python script via python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/tavily.py" to perform AI-citation probing. This script is part of the agent's local environment and is used to test content citability against search results.
  • [DATA_EXPOSURE]: The skill interacts with the local file system by reading entity profiles from memory/entities/ and saving deliverables to memory/content/. This is standard behavior for maintaining persistent project context and does not involve unauthorized data access.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text or content from external URLs for optimization. This process creates a potential attack surface for indirect prompt injection if the source data contains hidden instructions. The skill mitigates this risk by implementing a 5-step structured workflow, including a 'slop self-check' to strip AI-tell phrasing and a CORE-EEAT self-check matrix to validate output quality.
  • [EXTERNAL_DOWNLOADS]: The skill references numerous external resources for SEO and AI crawler guidelines. All linked domains (google.com, openai.com, perplexity.ai, anthropic.com, microsoft.com, brave.com) belong to well-known and trusted technology providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:02 PM
Security Audit — agent-trust-hub — geo-content-optimizer