Back to skill

Security audit

Skill Enhance

Security checks for vulnerabilities and agentic risk

Overview

This skill is a structured helper for creating and improving skill packages, with local edits limited to user-confirmed skill paths.

This skill is reasonable to install if you want help building or reviewing skills. Before allowing local modification, confirm the exact target path and intended edits, and review any changes because the skill is explicitly designed to update skill package files when asked.

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 (7)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
`SKILL.md` is the source of truth for the workflow.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 156)May include surrounding context.

md
`SKILL.md` is the source of truth for the workflow.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 249)May include surrounding context.

md
`SKILL.md` is the source of truth for the workflow.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 287)May include surrounding context.

md
`SKILL.md` is the source of truth for the workflow.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 305)May include surrounding context.

md
`SKILL.md` is the source of truth for the workflow.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 313)May include surrounding context.

md
`SKILL.md` is the source of truth for the workflow.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 492)May include surrounding context.

md
- Do not skip trigger-boundary review when the skill is meant to be reused.
- Do not skip artifact completion if the user is aiming for release.
- Do not force heavyweight benchmarking when lightweight validation is enough.
- Do not claim publish readiness without checking docs, evals, and packaging materials.
- Do not claim a local skill was modified unless the target path was accessible and the user confirmed the edit.
- Do not infer write access from mere path existence.
- Do not silently edit a downloaded or installed local skill without path confirmation.