ClawHub
Back to skill

Security audit

Crypto Drawdown Journal

Security checks for vulnerabilities and agentic risk

Overview

This is a simple prompt-only journaling skill for reflecting on crypto losses, with no evidence of file access, credentials, persistence, or hidden execution.

This appears safe to install as a reflective journaling aid. Users should still avoid sharing wallet credentials, private keys, account logins, or exact sensitive financial details, and should not treat it as financial or mental-health care.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The declared purpose is a prompt-only reflective journaling skill for crypto loss processing. The actual code chunk does not implement or demonstrate journaling behavior; instead, it tests that the handler resists local file access when given a suspicious skill name like '../../private-data'. This indicates a materially different primary purpose in the supplied code chunk: security/file-access handling rather than guided reflection. Because the observed behavior is unrelated to the declared user-facing function, this is a mismatch.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% 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 · SKILL.md (reported line 15)May include surrounding context.

md
1. Ask what happened: position, size, time horizon, and what the loss means in real life terms.
2. Separate the outcome from the decision process: was the decision reasonable given what was known?
3. Identify what was in the user's control versus what was not.
4. Surface emotional reactions and name them without judgment.
5. Extract 1-2 practical lessons without spiraling into self-punishment.

## Output Format

Static analysis

No suspicious patterns detected.