Back to skill

Security audit

RedNote Title Pack

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence; the main caveat is that its installation instructions use an unpinned command and a scanner flagged a mismatch between the stated reference-library purpose and installation activity.

The verdict is benign, but benign does not mean risk-free. Before installing, consider that the documented installer can fetch a changing CLI version; Skillspector recommends pinning and reviewing the installer and retrieved skill. The scan covered the text files, while the cover image was outside the static analyzers' supported content, so that part of the artifact was not assessed.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied chunk performs installation operations that can modify the local skill environment and, through npx, execute remotely obtained tooling. These capabilities are not disclosed in the description of a content-reference library. The package names align with the declared topic, but the chunk contains none of the advertised reference material. This assessment is limited to the supplied commands and does not establish the behavior of the referenced packages.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The documented installation command invokes an unversioned npm CLI through npx, potentially fetching and executing a changing package release with the user's permissions. This is a supply-chain hardening issue rather than an MCP-server issue: the command is ordinary installation documentation, not evidence of malicious behavior or automatic execution by the writing skill.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The release notes recommend executing an unversioned npm CLI through npx, so the installation can run a package release that changes independently of these notes. A compromised upstream release could execute code with the installer's permissions; however, this is an installation-time supply-chain risk, not an MCP reference or hidden behavior of the content-writing skill.

Content

No source excerpt is available for this finding.