ClawHub
Back to skill

Security audit

Crisis & Moderation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed social-crisis playbook that keeps public actions under human approval and does not contain executable or persistent behavior.

Before installing, users should understand that the skill may help pause, delete, or reschedule their own pending social posts through another scheduling skill, so they should review confirmations carefully. It should remain advisory for crisis responses and moderation decisions, with humans approving public wording and doing any platform moderation directly.

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
55% 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 46)May include surrounding context.

md
reply calmly or ignore. Don't escalate.
- **A legitimate complaint with traction** (a defective product, a bad interaction going semi-viral) →
  service recovery + empathy; handle well before it grows.
- **Misinformation / a false claim** → **correct the record with evidence**, don't apologize (see the
  deepfake note below and `the-response-playbook.md`).
- **A deepfake / synthetic outrage / coordinated attack** → AI-faked screenshots, bot-amplified
  "backlash." **Distinguish genuine dissatisfaction from a manufactured attack**; correct with evidence,

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
55% 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/triage-and-severity.md (reported line 23)May include surrounding context.

md
reply calmly or ignore. Don't escalate.
- **A legitimate complaint with traction** (a defective product, a bad interaction going semi-viral) →
  service recovery + empathy; handle well before it grows.
- **Misinformation / a false claim** → **correct the record with evidence**, don't apologize (see the
  deepfake note below and `the-response-playbook.md`).
- **A deepfake / synthetic outrage / coordinated attack** → AI-faked screenshots, bot-amplified
  "backlash." **Distinguish genuine dissatisfaction from a manufactured attack**; correct with evidence,