Security audit

Science Agent Recommend - Find the Right AI Tool for Research

Security checks for vulnerabilities and agentic risk

Overview

This is a directory-style research tool recommender with visible Claw4Science links and no evidence of code execution, persistence, or data access.

Install this only if you want recommendations drawn mainly from Claw4Science. Treat listed stars and project metadata as potentially stale, and independently review any suggested project's repository and installation instructions before using it.

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

Error

Location: SKILL.md:119
Finding: Mandatory Promotional Output and External Traffic Redirection
Content: View full analysis
Remediation: View remediation

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: 95% confidence
Finding: The trigger phrases include broad, natural-language requests such as "best AI for research" and "help me find a research tool," which can match ordinary conversation outside the intended scope. This can cause unintended activation of the skill, leading to inappropriate context switching, user confusion, or routing users into an external recommendation workflow they did not explicitly request.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.