ClawHub
Back to skill

Security audit

Iacuc Protocol Drafter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local IACUC draft generator, with no evidence of hidden network access, persistence, credential handling, or destructive behavior.

Install only if you want a local Chinese-language draft generator for IACUC protocol applications. Provide only protocol details you are comfortable storing locally, choose input and output paths deliberately, and have institutional IACUC or compliance staff review any generated application before use.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill declares file read/write behavior in its documentation and usage, but does not define an explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where an agent or reviewer cannot clearly enforce what file operations are intended, increasing the risk of unintended file access, path traversal, or writes outside the expected workspace if the backing script is permissive.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file description and generated document content are written in Chinese and present the skill as producing Chinese-language IACUC applications by default. Because the skill does not offer any language/locale opt-in or explain that it is intentionally restricted to a Chinese-speaking or region-specific context, it violates the language/locale policy criterion.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill description is overly broad and does not define when the skill should or should not be invoked, nor any exclusion conditions around sensitive content, regulated workflows, or file handling boundaries. In an agent setting, vague scope can cause overuse in inappropriate contexts and increase the chance of the tool being applied to unsafe or unauthorized tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.