dfyx-code-security-auditor
Fail
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's installation process requires cloning a repository from an unverified source ("https://github.com/EastSword/skill-dfyx_code_security_review.git"). This source is not recognized as a trusted organization or well-known service.
- [REMOTE_CODE_EXECUTION]: The functionality of the skill relies on the execution of multiple Python scripts (e.g., "code_scan.py", "vulnerability_validator.py", "pattern_scanner.py") downloaded from the external repository. Executing unverified scripts on a local machine poses a significant security risk.
- [COMMAND_EXECUTION]: The helper scripts documented in the skill are designed to perform complex operations, including file scanning and potentially running Docker containers ("--docker-verify"). These scripts have broad system access that could be misused if the downloaded content is malicious.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its analysis of untrusted data.
- Ingestion points: The skill ingests untrusted source code from the user's project (all files in the target directory).
- Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard malicious directives within the processed data.
- Capability inventory: The skill possesses capabilities to read files, execute shell commands via Python scripts, and manage Docker containers.
- Sanitization: No evidence of sanitization or filtering of input data before processing is mentioned in the skill definition.
Recommendations
- AI detected serious security threats
Audit Metadata