Security audit

Freelancer Bidder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Freelancer.com search and bid-drafting helper with disclosed local bid logging and no hidden code or privilege-seeking behavior.

Install this if you want an agent to search Freelancer.com, draft proposals, and keep a local bid log. Review generated proposals and bid prices before using them, and confirm before any real submission or workspace log update.

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

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 (7)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The manifest description says to use the skill when you want to 'find freelance jobs, write winning bid proposals, or monitor new project postings,' which is a broad natural-language trigger rather than a narrow activation condition. It does not define specific trigger phrases, scope limits, or exclusion conditions, so ordinary requests about freelance work or proposal writing could unintentionally invoke the skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The 'Tell the agent' section provides open-ended inputs like skills, budget, and tone, but does not specify exact invocation wording or when the skill should not activate. Because these are common conversational elements, the trigger surface is ambiguous and may overlap with unrelated requests.
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 metadata mixes Chinese description/features/triggers with English identifiers in a way that may steer interaction into a specific language without explicit user preference. This is risky because it can cause misunderstood actions, mistaken bids, or user confusion in a workflow that drafts external-facing proposals and tracks bidding activity.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger "Freelancer" is broad and likely to appear in normal conversation about freelancing, job platforms, or work history, which can cause unintended activation of the skill. In an agent environment, accidental invocation may lead to unsolicited scanning, proposal drafting, or exposure of user context to actions they did not explicitly request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The trigger "接单" is a common phrase meaning taking orders or accepting work, so it overlaps with ordinary user speech and can activate outside the intended context. This increases the risk of accidental execution when users discuss freelance work generally rather than intentionally invoking the skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The trigger "外包项目" is generic and describes a broad topic rather than a deliberate invocation phrase, making reliable activation control difficult. In this skill's context, unintended activation could start project searches or bid-drafting workflows based on incidental discussion of outsourcing projects.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill instructs the agent to maintain and update a persistent bids.md file in the workspace without warning the user that local files will be created or modified. Persistent writes can surprise users, overwrite existing content, or be abused through repeated invocation to alter workspace state in ways the user did not clearly authorize.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.