Back to skill

Security audit

kinetic-type-art

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill benign with medium confidence: the reviewed results show no executable scripts and no AIG findings, while flagging unpinned HyperFrames commands and a likely false positive; some evidence is incomplete.

The verdict is benign, not risk-free. Before installing, consider that the HyperFrames commands are unpinned and may run a changing package release. Skillspector inspected all 47 listed components, but marked analysis partial because a local reference was missing and bundled font binaries were outside its static analysis coverage.

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

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 · references/typeface-strobe.md (reported line 42)May include surrounding context.

md
- Similar faces back to back (two geometric sans) → swap is invisible; alternate silhouettes.
- No anchor → nothing to land on; end on the brand face and hold.
- Unlicensed commercial fonts copied from a famous sequence → use OFL equivalents.
- Full-frame flashing with no warning → keep the flash in the type [51].

## Sources
[8] @sarah_edo — https://x.com/sarah_edo/status/1231665606895624192 — recreating titles as practice

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

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The compatibility instructions reference npx hyperframes without an exact package version, allowing execution of a changing registry release when the package is not already installed locally. Although this is a rendering CLI rather than an MCP server, a compromised upstream release could execute code with the agent's permissions; the prose reference to version 0.8 does not pin the command.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The suggested npx hyperframes catalog command can fetch and execute an unpinned package, even though its apparent purpose is only to search a component catalog. This creates a supply-chain execution risk if the resolved release is compromised; the tool is a CLI, not an MCP server as the detector labels it.

Content

No source excerpt is available for this finding.