ClawHub
Back to skill

Security audit

present-workflow (from mk-present)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent presentation-planning workflow that may create a local markdown output file but does not show hidden, destructive, or credential-seeking behavior.

Before installing, expect the skill to guide an agent through research and planning for slide decks and to save the final approved plan under ./output/. Avoid putting secrets or private source material into the workflow unless you are comfortable with those details appearing in the generated markdown, and check before overwriting an existing output file.

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 (3)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to write a file to the local filesystem (./output/<name>.md) without requiring any user notification or confirmation. While the path is relatively constrained and intended for normal workflow handoff, silent file creation/modification is still a real security and transparency issue because it can surprise users, overwrite prior outputs, or violate least-astonishment expectations in restricted environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill includes a Chinese-only example request, and the document does not state that language should follow user preference or offer locale choice. This can imply a fixed language behavior without opt-in, which falls under language/locale policy concerns.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill explicitly directs the agent to create an ./output/ directory and save a file there, which modifies the user's filesystem. In this markdown file, there is no nearby warning or disclosure that the skill will create files/directories as part of execution.

Content

No source excerpt is available for this finding.