sql-sentinel

Fail

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The instructions guide the user to clone a repository from https://github.com/takeaseatventure/sql-sentinel.git, which is an unverified third-party source.
  • [COMMAND_EXECUTION]: The skill uses shell commands like git clone and node to manage and run external scripts.
  • [REMOTE_CODE_EXECUTION]: The skill requires running a JavaScript file (node scripts/sql-sentinel.js) that is downloaded from an external source, presenting a risk of executing malicious code.
  • [PROMPT_INJECTION]: Indirect injection risk found. Ingestion points: Reads SQL content from external files via path/to/query.sql (SKILL.md). Boundary markers: Absent; the script processes file contents directly. Capability inventory: Uses the node command to execute a script that parses the input (SKILL.md). Sanitization: Absent; the skill does not specify how external SQL content is sanitized before being analyzed by the LLM or the script.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 3, 2026, 03:26 AM
Security Audit — agent-trust-hub — sql-sentinel