ClawHub
Back to skill

Security audit

Upwork Proposal Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a single Markdown coaching skill for freelance proposal advice, with no hidden code, persistence, or data-access behavior found.

This skill is reasonable to install if you want freelance proposal coaching. Be aware it may activate on broad freelancing or pricing phrases, and independently verify platform policy details before acting on off-platform client guidance.

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
Confidence
95% confidence
Finding
The skill declares many broad trigger phrases such as 'win clients', 'fixed bid', 'hourly bid', and 'off-platform clients' that overlap with common freelancing discussions. This can cause unintended activation in unrelated contexts, leading the agent to inject bidding, pricing, or platform-circumvention guidance when the user did not request this skill, which is a scope-control and policy-safety issue.

Static analysis

No suspicious patterns detected.