Security audit

Freelancer Bidder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Freelancer.com job-search and bid-drafting helper with disclosed local bid logging and no executable code or hidden persistence.

Before installing, expect the agent to browse or query Freelancer.com for projects and to create or update a local bids.md bid-history file when you ask it to track bids. Review proposals before submitting them on any external account.

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 (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill description is broad enough to overlap with common user requests about finding freelance jobs, drafting proposals, or tracking bids, which increases the chance the agent invokes this skill in situations where the user did not explicitly request workspace changes or Freelancer-specific actions. That can lead to unintended external browsing and downstream actions such as creating or updating local files based on loosely related prompts.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The skill description is entirely in Chinese and describes the skill's behavior only in that language, which can indicate a language-specific experience without user opt-in. The manifest does not document that the skill is region-specific or offer a language choice.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger list includes broad terms such as 'Freelancer', 'freelance jobs', and generic Chinese phrases for gig work, which can activate the skill during ordinary conversation rather than clear user intent to use this specific automation. In an agentic setting, accidental invocation can lead to unintended browsing, proposal drafting, or bid-tracking actions on behalf of the user.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill instructs the agent to maintain a bids.md log in the workspace but does not warn users that local files may be created or modified. This creates a transparency and consent issue, because a user asking for job discovery or proposal drafting may not realize the skill can persist data to the workspace.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.