ClawHub
Back to skill

Security audit

damage-control

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local recovery playbook for agent failures, with some broad trigger wording but no hidden install, network, credential, or persistence behavior.

Before installing, be aware that this skill may be invoked by broad words like "state" or "context" and that its recovery procedures can change local git state. Use it when you want an agent to inspect and repair a broken worktree or interrupted session, and review proposed git stash, commit, restore, or abort actions before allowing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

High
Confidence
98% confidence
Finding
The manifest trigger list contains generic single words like "recovery," "crash," "context," "conflicts," and "state," plus a broad natural-language condition. These terms are common across many unrelated conversations and the file does not provide narrowing constraints or negative examples, increasing the chance of unintended invocation.

Skill Enumeration

Medium
Category
Agent Snooping
Content
- `../../risk-classification/modules/readiness-levels.md` - Level
  definitions
- `../SKILL.md` - Error recovery procedures
- `../../egregore/skills/quality-gate/SKILL.md` - Verification requirements
Confidence
80% confidence
Finding
skills/quality-gate/SKILL.md

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.