Back to skill

Security audit

Generate project documentation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed documentation generator that reads project code and writes Markdown files under docs/, with no evidence of hidden persistence, exfiltration, or destructive behavior.

Install only if you are comfortable with an agent reading project source and writing documentation under docs/. Review the overwrite/supplement choice carefully if docs/ already exists, and note that generated documentation is instructed to be written in Chinese with English technical terms.

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
  • 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 (10)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is designed to create multiple files under docs/ and may overwrite existing documentation, but the top-level description does not prominently warn users about this side effect. Although the body later mentions an overwrite/append prompt during precheck, users or calling systems may rely on metadata/description first, creating a risk of unintended file creation or replacement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction 中文编写,术语保留英文 forces a specific language for generated content. This is a language/locale policy issue because the file provides no user opt-in, alternative language option, or documented regional justification for restricting output to Chinese.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction 中文编写,术语保留英文。 mandates a specific language for the generated documentation. There is no opt-in, alternative language option, or documented justification that this skill must operate only in Chinese.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction '中文编写,术语保留英文' forces a specific language for the generated document. Because no user opt-in or language-choice mechanism is provided, this is a natural-language policy violation under the locale/language constraint rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction '中文编写,术语保留英文。' imposes a specific language requirement. Under the policy, forcing a language or locale without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction 中文编写,术语保留英文 forces a specific language for generated documentation. Under the policy, locale or language constraints should be optional or clearly justified; no opt-in or regional rationale is provided here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown prompt instructs the subagent to use the Write tool to create or overwrite docs/api.md and docs/data-model.md, which affects user files. The description contains no warning about file modification, overwrite risk, or need for user awareness before changing documentation outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The prompt explicitly instructs the subagent to use the Write tool to create or overwrite docs/architecture.md, but it does not include any warning, confirmation gate, or constraint around modifying repository files. In a documentation-generation skill this is expected behavior, but it still creates an integrity risk because the agent is authorized to change the working tree automatically and the user may not realize files will be written.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The prompt instructs the subagent to write directly to fixed paths under docs/ without requiring an existence check, backup, or user confirmation before overwriting. In a documentation-generation skill, this can unintentionally destroy or replace user-authored documentation, especially because the agent is expected to act autonomously and only return a one-line summary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown prompt explicitly directs the skill to run mkdir -p docs/modules and use a Write tool to create output files, which are file-system modifications. The file does not include any warning to the user that the skill will change the workspace or create files.

Content

No source excerpt is available for this finding.