complexity-analyzer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions are focused on code analysis and do not contain any patterns intended to bypass AI safety constraints or extract system prompts.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive file paths, or network exfiltration logic were detected.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not perform any external downloads or execute remote scripts. It mentions external tools (e.g., Radon, ESLint) as conceptual integrations but provides no code to install or run them.
- [Privilege Escalation] (SAFE): No commands related to administrative privileges or system-level modifications were found.
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze code provided by users (Category 8). While code could theoretically contain hidden instructions, the skill does not have executable capabilities (subprocesses, network access) that would allow an injection to perform meaningful damage. This is a standard risk for any code-analysis tool.
- [No Code] (SAFE): This skill is composed entirely of markdown instructions and does not ship with any executable scripts or binary files.
Audit Metadata