Security audit

Clawdtm Advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly an installer, but it gives an agent broad authority to download and activate remote skill files without enough local validation or user control.

Review this before installing. It is not evidence of malware, but it can install new skills that affect future agent sessions. Use it only if you trust the ClawdTM service and are comfortable with remote skill files being written locally; prefer manual review of the returned file list, paths, and contents before activation.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:94
Finding: Unverified Remote Skill Payload Retrieval and Activation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:111
Finding: Unvalidated Server-Controlled Installation Paths
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Rogue AgentSelf-Modification, Session Persistence
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 132)May include surrounding context.
md
{ "path": "SKILL.md", "content": "---\nname: memory-bank\n..." },

Session Persistence

Medium

Category: Rogue Agent
Confidence: 75% confidence
Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
Content: Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.
md
"slug": "memory-bank", "name": "Memory Bank", "author": "someuser", "description": "Persist context between sessions", "version": "1.2.0" }, "security": {

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill instructs writing fetched files into ./skills/{slug}/ in the current workspace, but does not explicitly warn that untrusted remote content will be materialized on disk. In an installer-oriented skill, that omission can cause users to approve installation without appreciating that arbitrary skill files, including scripts, may be introduced into their workspace and later executed by the agent ecosystem.
Content: No source excerpt is available for this finding.

Autonomous Decision Making

Medium

Category: Excessive Agency
Confidence: 75% confidence
Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
Content: Scanner excerpt · SKILL.md (reported line 157)May include surrounding context.
md
Example: "This skill makes network requests, which is expected for its purpose." ### medium (score 50-69) **Do not install without confirmation.** Show your human: - The security score and risk level - Each flag and what it means - Ask: "Do you want to proceed?"

Static analysis

No suspicious patterns detected.