ClawHub

Sailpoint

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate SailPoint integration, but it gives an agent broad authenticated access to sensitive identity-management operations without clear safety guardrails for changes.

Review before installing. Use only with a least-privilege SailPoint connection, prefer read-only discovery actions, confirm Membrane is approved for your organization, and require explicit human approval before creating, updating, deleting, disabling, or changing access-related records.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation description is broad enough that the skill could be selected for many generic requests involving identity, records, or workflows, increasing the chance it is invoked outside the user's precise intent. In a skill that can authenticate to an external identity platform and perform actions or proxy API requests, over-broad triggering raises the risk of unintended access, enumeration, or state-changing operations.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation describes running actions and raw proxy requests against SailPoint without an explicit warning that these operations may create, update, disable, or delete identities, accounts, or entitlements. Because SailPoint is an identity governance system, silent use of mutating operations can have significant operational and security consequences, including privilege changes or access disruption.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal