ClawHub
Back to skill

Security audit

medical-record-review

Security checks for vulnerabilities and agentic risk

Overview

This medical-record workflow has substantial safeguards, but broad activation terms could expose sensitive history during an unrelated request.

Restrict activation to explicit medical-record requests and require confirmation before opening the history when intent is ambiguous. Configure a separate folder for each person and decide whether hosted processing is acceptable. Keep clinician review and write-approval requirements in place.

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 · SKILL.md (reported line 50)May include surrounding context.

md
| **Output** | §7–§10 | conflicts and gates, evidence, risk lanes, output skeleton |
| **Maintain** | §11–§15 | housekeeping, structure, compression, TCM sub-flow, checklist |

A thirty-second answer may drop the optional work. It may never drop the safety rails.

| May skip on a quick answer | Never skipped, at any speed |
|---|---|

The trigger list includes unqualified everyday terms such as "review", "analysis", "index", "merge", "rename", and "audit" that overlap with unrelated tasks.

Medium
Category
Trigger Abuse
Confidence
97% confidence
Finding

Unqualified triggers such as "review", "analysis", "merge", and "audit" overlap with many unrelated tasks and can cause unintended skill activation if the host uses them for routing. This matters because the workflow directs the agent to read a medical-record history, potentially exposing sensitive information to a hosted model without a relevant user request. The medical description, configuration checks, and egress pre-check reduce the risk, but do not explicitly require confirmation that the current task concerns medical records.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.