Back to skill

Security audit

Skill Validation

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only skill validation checklist with some metadata quality problems, but no hidden code, persistence, credential use, or unsafe authority.

Before installing, expect this skill to function as a checklist for reviewing other skills. The publisher should fix the malformed frontmatter description and metadata inconsistency so the skill parses and activates predictably.

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 (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
- [ ] `SKILL.md` exists — the only hard requirement

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The body repeatedly instructs authors that the description must clearly state what the skill does and when to use it, typically with 'Use when' trigger phrasing. However, this file's description contains garbled DOT-like content and version-history text instead of a clean trigger-style description, contradicting the documented intent of the validator skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description says "Gunakan skill ini saat: validation" and "Aktif untuk tugas terkait skill-validation," which are broad activation cues without clear boundaries or negative examples. "validation" is generic enough to overlap with many routine tasks, making unintended invocation more likely.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file includes Indonesian in the frontmatter description while the rest of the document is predominantly English. This creates a natural-language policy concern because the skill implicitly imposes mixed language behavior without opt-in or documented locale justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The checklist says metadata must be a single-line JSON object due to a parser limitation, but this same skill file uses nested YAML for metadata in its own frontmatter. That is an active contradiction between the skill's instructions and what the file actually does, not merely an omission.

Content

No source excerpt is available for this finding.