ClawHub
Back to skill

Security audit

PubMed

Security checks for vulnerabilities and agentic risk

Overview

This is a simple PubMed research guidance skill with no executable code, persistence, credential handling, or hidden behavior.

This skill is appropriate to install for PubMed research help. Users should remember that language filters can exclude relevant non-English evidence and should apply them only when they fit the research question and available translation resources.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The guidance "Language filter if translation isn't feasible" is a natural-language instruction that can steer users toward restricting searches by language. Because the skill does not present this as a user choice with explicit opt-in or justify a required locale, it may conflict with language/locale policy expectations.

Static analysis

No suspicious patterns detected.