ClawHub
Back to skill

Security audit

Residency Interview Prep

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple residency interview practice tool with disclosed local Python execution and no evidence of network access, credential use, persistence, or hidden behavior.

Reasonable to install for residency interview practice. Users should treat medical, legal, and ethics prompts as interview preparation rather than professional advice, and should be aware that the skill's routing text is broader than necessary.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · scripts/main.py (reported line 58)May include surrounding context.

python
{
                "question": "A 17-year-old wants an abortion but doesn't want parents to know. How do you handle this?",
                "structure": "Legal requirements → Ethics → Patient-centered approach",
                "key_points": ["Know state laws", "Minor confidentiality", "Counseling without judgment", "Safety assessment"],
                "pitfalls": ["Personal bias", "Not knowing legal requirements", "Breaking confidentiality improperly"]
            }
        ]

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill's applicability criteria are overly broad, especially the statement that it should be used for general academic writing tasks with reproducible formatting. This can cause the agent to route unrelated requests into this skill, creating scope confusion and increasing the chance that users receive inappropriate outputs or that downstream script execution occurs under incorrect assumptions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.