Back to skill

Security audit

OKF Wiki MCP

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its commands use unpinned GitHub code that could change after review; the scanners did not report malicious behavior.

Consider whether you trust the upstream GitHub project before installing or running the commands. The scanner recommends using a reviewed, fixed version and limiting the tool's access to only the files and network it needs. The verdict is suspicious, not malicious; the reported issue is a potential risk, not evidence that harmful code ran.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

MCP server referenced without pinned version: 'npx github'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The stats command uses npx to execute code from a GitHub repository without pinning an immutable commit, so the code executed can change without any change to this skill. If the upstream repository or maintainer account is compromised, malicious code could run with the user's permissions and access sensitive meeting notes or other local files; the offline-workflow description does not enforce network isolation.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx github'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The search command executes an unpinned GitHub-sourced package, allowing upstream changes to alter the code run by users. A compromised upstream could execute arbitrary code under the user's account, and this skill's intended access to private meeting transcripts increases the potential confidentiality impact; no malicious behavior is demonstrated in the supplied file.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx github'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The actions command repeats the same mutable GitHub execution reference, creating another entry point for the same supply-chain risk rather than a distinct underlying flaw. If upstream code is maliciously changed, running this apparently read-only query could execute attacker-controlled code with access to confidential action items and other files available to the user.

Content

No source excerpt is available for this finding.