ClawHub
Back to skill

Security audit

Flow Cytometry Gating Strategist

Security checks for vulnerabilities and agentic risk

Overview

The skill is an offline flow-cytometry recommendation script with optional user-directed JSON output and no evidence of hidden network, persistence, credential, or destructive behavior.

This skill appears reasonable to install for offline gating-strategy recommendations. Treat the generated guidance as experimental support rather than clinical or regulatory advice, and use the optional --output path carefully so it does not overwrite an important file. The publisher should clean up the metadata because it claims Network/API access that the current script does not actually 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill advertises executable/script behavior and file write capability, but it does not declare any explicit tool scope such as permissions or allowed-tools. In an agent environment, that omission weakens containment and makes it easier for the skill to obtain broader-than-intended filesystem access or be executed without clear operator review.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation states that the skill may perform external API calls and read/write data, but it does not provide a clear user-facing warning about what data could leave the environment or what files may be modified. For a bioinformatics skill that may process experimental or potentially sensitive research data, this creates a meaningful privacy and system-integrity risk through uninformed use.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
This code file contains user-facing natural-language content in Chinese in the module docstring and command-line usage/help text. Because the skill does not offer an English/Chinese selection or document the locale restriction as intentional, it may violate a language-choice policy for general users.

Description-Behavior Mismatch

Low
Confidence
86% confidence
Finding
The manifest frames the skill as a recommender for flow cytometry gating strategies, but the code also performs filesystem writes when an output path is provided. Persisting results to disk is beyond the core recommendation behavior described in the manifest, even though it is auxiliary rather than harmful.

Static analysis

No suspicious patterns detected.