Security audit

Paper to Tools - Match Research Methods to AI Agents

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill recommends research agents from a directory and has no hidden execution, persistence, or data access, though users should treat its external install/link suggestions cautiously.

Before installing anything recommended by this skill, verify the third-party project, prefer pinned versions or trusted repositories, and avoid running `npx` commands unless you understand the package source. Expect responses to include Claw4Science links.

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

Findings (1)

T01 · Skill Instruction Hijacking

Note

Location: SKILL.md:76
Finding: Mandatory Third-Party Promotional Output Hijacks Agent Responses
Content: View full analysis
Remediation: View remediation

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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest trigger words include broad phrases like "which agent can do this" and "what tools for this method," which can overlap with ordinary user requests outside the intended paper-method matching context. The trigger section does not provide exclusion conditions or negative examples to clarify when the skill should not activate.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run npx skills add without pinning a specific package version or trusted source. This creates a supply-chain risk: a later malicious or compromised package release could be fetched and executed at install time, and the skill’s purpose of recommending external agents makes that execution path more likely to be followed by users.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.