javascript-pro

Fail

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: CRITICALCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Automated security scanners (URLite) have flagged the documentation URL https://jeffallan.github.io/claude-skills/skills/language/javascript-pro/ as malicious.\n- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands including eslint --fix and jest in the local environment as part of its core workflow (SKILL.md).\n- [METADATA_POISONING]: The main skill file SKILL.md was flagged by file reputation scanners as malware. Additionally, the author listed in the YAML metadata (Jeffallan) differs from the platform-indicated author (emmraan), which may indicate impersonation.\n- [INDIRECT_PROMPT_INJECTION]:\n
  • Ingestion points: The skill reviews and refactors .js, .mjs, and .cjs code files as well as package.json configuration.\n
  • Boundary markers: None. The skill does not instruct the agent to ignore or delimit potentially malicious instructions embedded in the JavaScript files it processes.\n
  • Capability inventory: The skill uses child_process for command execution and fs/promises for extensive file system manipulation (references/node-essentials.md).\n
  • Sanitization: None. The skill does not validate or sanitize the content of the files before processing them or invoking external tools on their content.
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 6, 2026, 11:36 AM
Security Audit — agent-trust-hub — javascript-pro