ClawHub
Back to skill

Security audit

Coding Tutor

Security checks for vulnerabilities and agentic risk

Overview

This is a programming tutor skill with harmless decoded content, though its Base64 packaging makes it harder to review and may affect compatibility.

Review the decoded skill text before installing because the package is not stored as plain Markdown. Functionally, it appears to be a standard coding tutor, but the publisher should replace the Base64 line with readable SKILL.md content for easier review and compatibility.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Note
Location
SKILL.md:1
Finding

Entire Skill Definition Is Obfuscated with Base64 Encoding

Content
View full analysis

Vulnerability Details

File Location: SKILL.md:1
Vulnerability Type: Obfuscated and non-parseable skill configuration
Risk Level: Low

Complete Code Snippet:

text
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
...[truncated 4855 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace the Base64 line with the decoded UTF-8 Markdown so the YAML front matter and instructions are directly reviewable.
  2. Validate SKILL.md during continuous integration, requiring readable Markdown and parseable YAML front matter.
  3. Reject files whose content is predominantly high-entropy Base64 unless encoding is explicitly required and independently reviewed.
  4. Add decoded-content inspection to security scanning where encoded artifacts are legitimately permitted.
  5. Require review of semantic changes to skill instructions rather than relying only on diffs of encoded data.
  6. Preserve the decoded file in version control so future changes produce meaningful, auditable line-level diffs.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The natural-language content in the skill description and body is presented entirely in Chinese, with no indication that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.