Back to skill

Security audit

Logo Svg Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a logo-design helper that writes local SVG/PNG outputs and does not show hidden, destructive, credential-seeking, or persistence behavior.

Install only if you want an agent-guided logo generator and are comfortable with local files being created under output folders. If a future package includes the referenced Python scripts, review those scripts before running them, especially any CDN fetching or deploy helper, because they were not present as executable code in this inspected artifact.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
rkdown + Python bundle. It runs anywhere a coding agent or LLM tool can load a `SKILL.md` and call local scripts — including but not limited to **TRAE, Opencode

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
The skill uses an **iterative visual-review loop**: generate → rasterize → visually inspect (vision LLM) → critique → optimize → re-inspect → finalize.

> **Portable / agent-agnostic.** This skill is a plain Markdown + Python bundle. It runs anywhere a coding agent or LLM tool can load a `SKILL.md` and call local scripts — including but not limited to **TRAE, Opencode, Claude Code, Hermes, openclaw**, Cursor, Continue, or a custom harness. Any reference to "the agent" / "the host" below applies uniformly to all of them.

---

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The edge-case guidance explicitly singles out users in mainland China and prescribes different CDN behavior for that locale. Under the policy rule, locale-specific behavior should either be user-selectable or clearly justified; here it is presented as automatic behavior without an opt-in choice.

Content

No source excerpt is available for this finding.