skills/jeremylongshore/claude-code-plugins-plus-skills/cursor-api-key-management/Gen Agent Trust Hub
cursor-api-key-management
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requests broad shell access via the Bash tool to perform configuration checks and troubleshooting.\n
- Evidence:
SKILL.mdspecifiesallowed-tools: "Read, Write, Edit, Bash(cmd:*)".\n - Evidence:
references/troubleshooting.mdincludes examplecurlcommands for API testing.\n- [DATA_EXFILTRATION]: The skill is designed to read from and write to sensitive configuration files that contain authentication secrets.\n - Evidence:
references/configuration-methods.mdreferences~/.config/Cursor/User/settings.json,~/.zshrc, and~/.bashrcas primary configuration targets.\n - Evidence:
references/security-best-practices.mdprovides commands to inspect and modify permissions on these sensitive files.\n- [PROMPT_INJECTION]: The skill establishes a high-capability environment that interacts with sensitive data files, creating a surface for indirect prompt injection.\n - Ingestion points: User configuration files and shell profiles (
references/configuration-methods.md).\n - Boundary markers: None present to distinguish between legitimate configuration and embedded instructions.\n
- Capability inventory: Full file manipulation (
Read,Write,Edit) and shell execution (Bash) capabilities (SKILL.md).\n - Sanitization: No evidence of input validation or escaping for data retrieved from these files.
Audit Metadata