Back to skill

Security audit

SciProjDesigner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a domain-specific computational drug discovery and molecular modeling advisor with no hidden execution, credential use, persistence, or broad local access.

Install this if you want a rigorous scientific reviewer for computational biology or drug discovery workflows. Expect a critical tone and structured methodology audits; generic coding help should use this skill mainly when the code is clearly related to NumPy, MDAnalysis, RDKit, OpenMM, or similar molecular modeling work.

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
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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger conditions include generic behaviors like sharing code for optimization, debugging, or peer review, which are common across many domains and not unique to this skill. This overlap makes accidental activation more likely, potentially causing the agent to apply domain-specific instructions in contexts where a general coding or analysis skill would be safer and more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger conditions include generic behaviors like sharing code for optimization, debugging, or peer review, which are common across many domains and not unique to this skill. This overlap makes accidental activation more likely, potentially causing the agent to apply domain-specific instructions in contexts where a general coding or analysis skill would be safer and more appropriate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.