ClawHub
Back to skill

Security audit

job-poster

Security checks for vulnerabilities and agentic risk

Overview

This job-posting skill is simple and not malicious, but it asks for authority to publish job listings without enough scoping, confirmation, or included implementation details.

Install only if you can verify the missing job_poster.py implementation and understand the destination service. Before use, require explicit confirmation of the posting target, final listing content, and the user's authority to publish or update the job listing; use a narrowly scoped API key if possible.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill's trigger conditions are broad and underspecified, such as 'Automating job tasks' and 'Hr operations', which can cause an agent to invoke this skill in contexts unrelated to posting jobs. Overly permissive routing increases the chance of unintended execution, potentially leading to accidental publication of sensitive, incorrect, or unauthorized job listings.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.