seo-technical

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data and local project documentation, creating a surface for indirect prompt injection.
  • Ingestion points: Fetches website HTML content via curl commands and reads local files and metadata from an Obsidian vault (.md notes and .obsidian directory).
  • Boundary markers: No specific boundary markers or delimiters are instructed to isolate ingested external content from internal instructions.
  • Capability inventory: The skill uses shell commands (curl) and executes local Python scripts (scripts/seo_audit.py, skills/seo-internal-linking/scripts/site_crawl.py) via subprocess calls.
  • Sanitization: The instructions do not define specific methods for sanitizing or validating retrieved external data before processing.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands and Python scripts as part of its technical SEO workflow.
  • Evidence: Direct instructions for the agent to run python3 scripts/seo_audit.py and curl -sL for auditing status codes, headers, and content visibility.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 05:40 PM