javascript-pro

Fail

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Automated security analysis tools have identified components of this skill as malicious.\n
  • The URL https://jeffallan.github.io/claude-skills/skills/language/javascript-pro/ is currently blacklisted by security reputation providers.\n
  • The file SKILL.md is flagged with a malicious reputation (FileRepMalware [Misc]) by file reputation scanners.\n- [EXTERNAL_DOWNLOADS]: The skill instructs agents to reference external resources on a domain (jeffallan.github.io) that is currently associated with malicious activity, potentially leading to the execution of untrusted logic or instructions.\n- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of external source code without sufficient isolation or sanitization.\n
  • Ingestion points: The skill is designed to read and analyze .js, .mjs, .cjs, and package.json files.\n
  • Boundary markers: There are no instructions to use delimiters or ignore instructions embedded in the processed files, which could lead to an agent following malicious commands hidden in code comments or strings.\n
  • Capability inventory: The skill documentation provides examples and instructions for using powerful system capabilities, including network requests (fetch), file system access (fs/promises), and subprocess execution (child_process.spawn, exec).\n
  • Sanitization: The skill lacks any requirement or mechanism to validate or sanitize external file content before it is incorporated into the agent's context.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 14, 2026, 03:58 PM
Security Audit — agent-trust-hub — javascript-pro