ClawHub
Back to skill

Security audit

Primer Design Check

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple primer-check script, but it advertises off-target BLAST/template analysis that the code does not implement.

Review before installing or relying on results. This appears locally contained, but users should treat it as a basic primer property checker only and should not rely on it for off-target specificity, BLAST results, or template-genome validation unless those features are actually added.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The implemented behavior mostly aligns with the stated primer-quality checking purpose, specifically for hairpins and dimers. However, the description explicitly claims off-target amplification checking, which the code does not do at all: there is no genome/database search, alignment, specificity analysis, or any other off-target detection logic. This is a material description-to-behavior mismatch because one of the listed core checks is absent.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises off-target amplification checking, but the implementation only evaluates simple primer-intrinsic properties such as Tm, GC content, hairpins, and self-dimers. In a bioinformatics or lab-support context, this mismatch can mislead users into trusting the tool for specificity screening, potentially causing selection of primers with significant off-target binding risk.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

Labeling the routine as a 'Comprehensive primer check' overstates what the code actually does and reinforces the false impression that all key primer quality dimensions are covered. In this skill's scientific workflow context, overstated analytical coverage can lead to misuse and incorrect experimental decisions even though no traditional code-execution primitive is present.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.