Dark Matter Analyzer
Fail
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [Prompt Injection] (HIGH): The skill possesses a significant Indirect Prompt Injection surface (Category 8). It is designed to process untrusted data (repository contents) and has the capability to modify files and create artifacts. A malicious file within an analyzed repository could contain instructions that redirect the agent's logic to delete data or inject backdoors.\n
- Ingestion points: Full repository access including code, docs, and metadata.\n
- Boundary markers: None identified.\n
- Capability inventory:
modifies_files,creates_artifacts.\n - Sanitization: No evidence of sanitization or instruction filtering for analyzed content.\n- [Command Execution] (MEDIUM): The documentation promotes the use of
dark-matter-analyzer-mcp, an unverified third-party tool. Executing the suggested CLI commands (dark-matter scan) could lead to the execution of untrusted code if the agent attempts to install or run this external dependency.
Recommendations
- AI detected serious security threats
Audit Metadata