ClawHub
Back to skill

Security audit

Confession Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple writing template for anonymous crypto loss stories and does not request tools, persistence, credentials, or system access.

Before installing, treat this as a creative writing helper rather than financial guidance. Review generated posts for accuracy, avoid presenting invented confessions as real unless appropriate, and keep the built-in anonymization rules when using any real user-provided details.

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
  • 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
  • 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 · SKILL.md (reported line 23)May include surrounding context.

md
1. **First person** — "I", not "you" or "one should"
2. **Specific numbers** — exact dollar amounts, exact percentages, exact time periods
3. **No moralizing** — show the damage, don't preach about it
4. **No identifying details** — never include project names, specific dates that could identify someone, or wallet addresses
5. **Real emotion, not performance** — the confessions that land are the ones where you can feel the person processing what happened, not performing regret
6. **End with what they'd do differently** — one specific change, not "I learned to be careful"

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 52)May include surrounding context.

md
2. Generate the confession following the format rules above.

3. Return the confession ready to post. No disclaimers needed within the text itself.

## Example Output Format

Static analysis

No suspicious patterns detected.