Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This is a small process-listing skill with no evidence of hidden execution, network access, persistence, or destructive behavior.
Install only if you are comfortable letting the skill display local process command lines. It appears bounded and non-persistent, but process arguments may expose sensitive strings if other programs put secrets on their command line.
Without declared permissions the skill's intent is opaque and cannot be validated.