Back to skill

Security audit

Shadows Skill Factory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward helper for drafting and saving new skill files, with only minor disclosure and trigger-scope caveats.

Before installing, understand that this skill is meant to draft and potentially save new SKILL.md files. Review any generated skill carefully, especially its trigger conditions, requested tools, credentials, shell commands, and network access, before adding it to your agent or publishing it.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The trigger phrases are broad enough that the skill may activate in ordinary discussion about creating skills, not only when the user intends to invoke this specific meta-skill. Overbroad activation can cause unintended instruction injection into unrelated workflows and may lead an agent to generate or save files unexpectedly in the wrong context.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill's SECURITY CONSIDERATIONS section asserts it does not modify files, yet the documented workflow and output explicitly describe creating a directory and writing SKILL.md to disk. This mismatch can mislead users and downstream reviewers about the skill's actual side effects, reducing scrutiny around filesystem writes and making unsafe automation easier to approve.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.