ClawHub
Back to skill

Security audit

qmd Local Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local-search helper for indexed markdown/docs and does not show hidden, destructive, or exfiltrating behavior.

Install only if you want agents to use qmd for local indexed search. Keep collections scoped, avoid indexing sensitive directories unless intended, and remember that adding collections or embeddings may create local indexes and download local model files.

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
  • 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

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description instructs the agent to use this skill broadly for generic tasks like file discovery, code search, and documentation lookup, which overlaps with many common workflows. Overly broad activation criteria can cause the skill to be invoked unnecessarily, increasing the chance that its guidance supersedes safer or more appropriate tools and expanding exposure to any downstream tool misuse or prompt-injection content in searched files.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The "When to Use" section lists broad triggers such as finding files, code discovery, and context gathering without clear limits or conditions. This ambiguity can make the agent over-select the skill in situations where narrower tools would be safer or more precise, creating unnecessary access to large local content sets and amplifying the effect of any malicious or irrelevant indexed content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.