ClawHub
Back to skill

Security audit

moltlang

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small symbolic-language reference with disclosed, user-directed install instructions and no hidden execution or data access found.

Review the skill text before installing and prefer a trusted package or a pinned revision/checksum if you use the curl option. Re-running the update commands can replace the local skill with newer remote content, but the inspected artifact itself is only a language/codebook reference and shows no hidden execution, credential access, or destructive behavior.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README instructs users to download remote SKILL.md and codebook.json files directly into the local skills directory and overwrite any existing copies, without integrity verification, version pinning, or warning about trust boundaries. Because skills influence agent behavior, this creates a supply-chain style risk where a compromised repository, network path, or future update could silently change local agent behavior.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
84% confidence
Finding

The instructions create a persistent local skill directory and place remotely fetched files into it, making the behavior change survive across future agent sessions. Persistent installation increases risk because a one-time unsafe fetch can become a long-lived trusted component that continues influencing agent actions until manually removed or updated.

Content

Scanner excerpt · README.md (reported line 32)May include surrounding context.

Option 2: curl (no dependencies)

bash
mkdir -p ~/.moltbot/skills/moltlang
curl -sL https://raw.githubusercontent.com/eduarddriessen1/moltlang/main/SKILL.md > ~/.moltbot/skills/moltlang/SKILL.md
curl -sL https://raw.githubusercontent.com/eduarddriessen1/moltlang/main/codebook.json > ~/.moltbot/skills/moltlang/codebook.json

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% 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 18)May include surrounding context.

Or curl the files directly:

bash
mkdir -p ~/.moltbot/skills/moltlang
curl -s https://raw.githubusercontent.com/eduarddriessen1/moltlang/main/SKILL.md > ~/.moltbot/skills/moltlang/SKILL.md
curl -s https://raw.githubusercontent.com/eduarddriessen1/moltlang/main/codebook.json > ~/.moltbot/skills/moltlang/codebook.json

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 33)May include surrounding context.

Or curl the files directly:

bash
mkdir -p ~/.moltbot/skills/moltlang
curl -s https://raw.githubusercontent.com/eduarddriessen1/moltlang/main/SKILL.md > ~/.moltbot/skills/moltlang/SKILL.md
curl -s https://raw.githubusercontent.com/eduarddriessen1/moltlang/main/codebook.json > ~/.moltbot/skills/moltlang/codebook.json

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

Or curl the files directly:

bash
mkdir -p ~/.moltbot/skills/moltlang
curl -s https://raw.githubusercontent.com/eduarddriessen1/moltlang/main/SKILL.md > ~/.moltbot/skills/moltlang/SKILL.md
curl -s https://raw.githubusercontent.com/eduarddriessen1/moltlang/main/codebook.json > ~/.moltbot/skills/moltlang/codebook.json

Static analysis

No suspicious patterns detected.