seo-backlinks

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill frequently invokes shell commands to execute Python scripts located in the local scripts/ directory (e.g., python scripts/backlinks_auth.py, python scripts/moz_api.py, python scripts/verify_backlinks.py).
  • [COMMAND_EXECUTION]: An installation script at ./extensions/dataforseo/install.sh is mentioned for setting up the DataForSEO extension.
  • [EXTERNAL_DOWNLOADS]: The skill references downloading domain-level graphs from Common Crawl and interacts with external APIs like Moz, Bing Webmaster, and DataForSEO.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external URLs and user-supplied link files, which creates a surface for indirect prompt injection.
  • Ingestion points: Processes data from the <url> argument and --links <file> inputs.
  • Boundary markers: None explicitly defined in the instructions for separating untrusted data from agent instructions.
  • Capability inventory: The skill possesses command execution capabilities through several local Python scripts.
  • Sanitization: No automated sanitization is described, although a 'Pre-Delivery Review' checklist is included to verify data consistency manually.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 05:55 AM