Security audit

debate-research

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent debate-research skill that uses subagents and web search for its stated purpose, with manageable prompt-injection and installer-version risks users should understand.

Before installing, consider pinning the ClawHub installer version instead of using @latest. When using the skill on consequential topics, verify important sources yourself because web content and earlier agent outputs are reused in later debate phases and could bias the final report.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:66
Finding: Untrusted Web-Derived Content Is Recursively Injected into Agent Prompts
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: README.md:55
Finding: Installation Documentation Executes a Mutable Latest Package Release
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Anti-Refusal Statement

High

Category: Anti-Refusal
Confidence: 85% confidence
Finding: Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
Content: Scanner excerpt · references/prompts.md (reported line 83)May include surrounding context.
md
Do NOT judge who is right or wrong. Only audit evidence quality.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 96% confidence
Finding: The install command uses npx clawhub@latest, which fetches and executes the latest published package rather than a pinned, reviewed version. If the package is compromised, a malicious release is published, or the publisher account is hijacked, users installing the skill could execute attacker-controlled code during setup.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.