ClawHub
Back to skill

Security audit

McKinsey-style Decision Memo Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward memo-writing helper with no code execution, persistence, credential access, or hidden data handling.

Install this if you want help turning provided documents or threads into concise decision memos. For sensitive contracts, financial, legal, or medical material, treat the output as a summary aid and get qualified review before acting on it.

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
85% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 193)May include surrounding context.

md
Extract the real issue, the current status, unresolved questions, and concrete next steps.

### If the user gives very little context
Do not refuse. Infer the likely decision context and produce a useful memo anyway.

## Quality bar

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The example prompts are broad, generic requests for summarization and memo writing that overlap heavily with normal assistant usage. If the skill activation relies on loose natural-language matching, it can be triggered unintentionally on many unrelated user requests, causing the wrong skill to handle sensitive documents or override the user's expected workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.