hunt-laravel

Fail

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads code from an external GitHub repository.
  • Evidence: git clone https://github.com/ambionics/laravel-ignition-rce /tmp/laravel-rce in SKILL.md.
  • [REMOTE_CODE_EXECUTION]: The skill executes a downloaded script using the PHP interpreter, which could lead to arbitrary code execution if the source is compromised.
  • Evidence: php /tmp/laravel-rce/exploit.php https://$TARGET "id" in SKILL.md.
  • [DATA_EXFILTRATION]: The skill explicitly targets sensitive files that contain credentials, API keys, and environment variables.
  • Evidence: Commands accessing /.env, /.env.production, and /storage/logs/laravel.log in SKILL.md.
  • [COMMAND_EXECUTION]: The skill makes extensive use of shell commands to fingerprint targets and execute exploits.
  • Evidence: Usage of curl, grep, php, and python3 -m json.tool across various phases in SKILL.md.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes unvalidated content from external web servers.
  • Ingestion points: Output from curl requests to $TARGET in SKILL.md.
  • Boundary markers: None present to separate external content from instructions.
  • Capability inventory: Shell execution via git clone, php, and python3 in SKILL.md.
  • Sanitization: No evidence of output sanitization or validation before processing.
  • [NO_CODE]: The skill instructions reference an external script laravel_cookie_forge.py which is missing from the provided skill files.
Recommendations
  • HIGH: Downloads and executes remote code from: https://$TARGET/telescope/api/redis, https://$TARGET/telescope/api/requests, https://$TARGET/telescope/api/commands - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 31, 2026, 04:47 PM
Security Audit — agent-trust-hub — hunt-laravel