ClawHub
Back to skill

Security audit

TalentHR

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed TalentHR connector skill with a scoped write action, though users should be cautious about the CLI install command.

Install only if you intend to let the agent use your OOMOL-connected TalentHR account. Review any role-change payload before approval, and consider using OOMOL’s official install guide instead of running pipe-to-shell installer commands blindly.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs users to install software via a remote script piped directly into a shell (curl ... | bash), which executes network-fetched code without prior verification. If the hosting source, transport path, or supply chain is compromised, this can result in arbitrary code execution on the user's machine; in this skill context, the danger is heightened because the command is presented as an authentication/setup fallback that users may trust and run verbatim.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description says to use this skill for "ANY TalentHR request" and "Whenever a task involves TalentHR," which is extremely broad and overlaps with many routine conversations or tasks mentioning TalentHR. The file does not provide narrower trigger constraints, exclusions, or negative examples to clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.