seo-bing

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local scripts (bing_webmaster.py, indexnow_submit.py) via a claude-seo wrapper to perform its primary functions.
  • [COMMAND_EXECUTION]: The instructions require the user to manually run installation scripts (install.sh or install.ps1) provided within the extension directory for setup.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from URLs and batch files, which could potentially be used to influence agent behavior if the indexing tools do not properly sanitize inputs.
  • Ingestion points: The skill ingests data through URL parameters and batch file paths in the /seo bing submit and /seo bing submit-batch commands.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are included in the prompt instructions.
  • Capability inventory: The skill possesses the capability to execute shell commands and make network requests via its internal Python scripts.
  • Sanitization: There is no evidence of input validation or sanitization for the URL data processed by the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 09:07 PM
Security Audit — agent-trust-hub — seo-bing