Back to skill

Security audit

create-docs-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent documentation-to-skill workflow with normal web and file operations, but users should supervise cleanup and any changes to existing skills.

Install only if you want an agent workflow that can scrape documentation, generate files, package skills, and potentially merge with existing same-topic skills. Review the target directory before running cleanup commands and approve any modification of existing installed skills.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill content is written entirely in Chinese and does not instruct the agent to preserve or negotiate the user's preferred language, effectively biasing outputs toward a specific language across the full workflow. This can cause the agent to ignore user language expectations, degrade reliability, and produce unusable or misleading results in multilingual environments.

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
97% confidence
Finding

The skill instructs the agent to run a destructive recursive deletion command (rm -rf references/documentation/) during packaging. If path assumptions are wrong, variables are expanded unexpectedly, or the working directory is not what the skill expects, this can delete unrelated files and cause irreversible data loss.

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

skill-seeker 默认会生成 5 层深路径,必须手动扁平化:

bash
mv references/documentation/xxx-docs_docs/* references/
rm -rf references/documentation/

然后 package_skill 打包。

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill's trigger description is broad enough to activate on many common documentation-related requests, which can cause the agent to invoke this skill in situations where it is not the best fit. Over-broad activation increases the chance of inappropriate tool use, unnecessary web scraping, or applying this workflow to unrelated tasks without clear user intent.

Content

No source excerpt is available for this finding.