ClawHub
Back to skill

Security audit

Scan

Security checks for vulnerabilities and agentic risk

Overview

The skill is only a Markdown instruction file, but it broadly asks agents to process sensitive biometric, genomic, legal, network, code, and spatial data without clear user consent or scope limits.

Review this carefully before installing. It does not contain executable malware, but it is written to encourage broad analysis of highly sensitive data. Only use it where you have authorization for the data involved, and prefer a version that requires explicit user confirmation and clear limits for biometric, genomic, legal, network, code, and spatial inputs.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description explicitly advertises telemetry, biometric, and high-density information extraction, which are sensitive processing domains, but provides no privacy warning, consent requirement, retention limits, or legal/compliance framing. This is dangerous because an agent may route highly sensitive personal data into the skill without informed user approval or appropriate handling safeguards.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The body expands the skill's scope to genomic analysis, packet-level network analysis, vulnerability detection, litigation document review, and environmental mapping—each a high-impact domain involving sensitive, regulated, or dual-use data—yet still omits warnings and operational safeguards. The context makes this more dangerous, not less, because the skill is framed as a universal ingestion layer that can normalize and cross-reference diverse sensitive inputs at speed, increasing the chance of broad surveillance, unauthorized analysis, or harmful autonomous use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description is extremely broad and markets the skill as a general-purpose deep-scan interface for many data types without defining narrow invocation boundaries, permitted inputs, or safety constraints. In an agent ecosystem, this can cause over-invocation on sensitive materials and create privacy, compliance, and misuse risks because the skill appears applicable to almost any high-value dataset.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.