ClawHub
Back to skill

Security audit

Dont Deal Triage

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed local health-triage helper, but its package is incomplete and users should be aware it asks the agent to inspect limited local work-pattern data.

Before installing, understand that this skill may cause an agent to consider limited local work-pattern data, such as git timestamps, while discussing health symptoms. Because the package references missing scripts and reference files, it may not work as described unless those files are added; do not treat its output as medical diagnosis, and require explicit consent before any local context inspection or storage of health history.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill activation criteria are broad enough to trigger on common symptoms or a generic 'health check,' causing a coding assistant to enter quasi-medical triage mode in situations where the user may not have intended that scope. Because the skill also instructs the agent to inspect local git and host context, accidental activation can lead to unnecessary collection and use of sensitive local data in a health-related context.

Content

No source excerpt is available for this finding.

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
75% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
## Response rules

- Never reassure the user that symptoms are "just stress" or "probably not serious."
- Never tell the user to drive themselves to the hospital when emergency symptoms are active.
- Tell the user to reduce activity immediately if chest pain is ongoing.
- If emergency care is indicated, stop discussing code or work until the user confirms they are safe.
- Treat git activity as a weak fatigue signal, not evidence about the user's exact sleep duration.

Static analysis

No suspicious patterns detected.