seo-bing

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONNO_CODEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines mappings that execute local scripts via the shell, including python scripts/bing_webmaster.py and python scripts/indexnow_submit.py.- [NO_CODE]: The skill references several external files, including an installation script (extensions/bing-webmaster/install.sh) and utility scripts (scripts/bing_webmaster.py, scripts/indexnow_submit.py), which are not provided for analysis.- [PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by processing external data (URLs and files) as command arguments. 1. Ingestion points: <url> and <file> parameters in the routing table for commands like /seo bing submit and /seo bing submit-batch. 2. Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present to isolate the untrusted input. 3. Capability inventory: Execution of local Python scripts via the python command. 4. Sanitization: No input validation or sanitization logic is present in the instruction markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:37 AM
Security Audit — agent-trust-hub — seo-bing