Back to skill

Security audit

OpenClaw Doc Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a documentation helper, but it overstates several capabilities and includes repository-writing workflows without enough safeguards or warning.

Review this skill before installing. Use it only on a test branch or with a clean diff, avoid copying the CI workflow as-is, and constrain source/output paths. Expect only basic Python API documentation and README TOC updates unless the missing features are implemented.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

If the implementation really lacks the advertised API generation, architecture diagram generation, and broad sync behavior, then the skill overstates what it does and may cause users or agents to trust it for actions it cannot safely or correctly perform. Misrepresentation of behavior is dangerous in agent skills because operators may grant write access or automation authority based on inaccurate expectations.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

If the implementation really lacks the advertised API generation, architecture diagram generation, and broad sync behavior, then the skill overstates what it does and may cause users or agents to trust it for actions it cannot safely or correctly perform. Misrepresentation of behavior is dangerous in agent skills because operators may grant write access or automation authority based on inaccurate expectations.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill documents file-reading and file-writing behavior through commands that generate and update documentation, but it does not declare any explicit tool scope such as allowed-tools or permissions. This increases the chance that an agent executes the skill with broader file access than intended, making unintended project modifications more likely.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The primary descriptive text and feature explanations are written in Chinese, while the file also contains English headings, suggesting a mixed-language audience. There is no statement that the skill is intentionally Chinese-only or that users can choose their preferred language, which creates a language/locale policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises automatic README and documentation updates without clearly warning that it modifies repository files. In an agent context, silent write behavior can lead to unreviewed content changes, accidental overwrites, or documentation poisoning if generated from untrusted source content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The auto-fix mode is presented as a convenience feature but does not warn that it can create or regenerate files automatically. In automated environments this can overwrite expected outputs, introduce noisy diffs, or propagate malformed generated content into the repository.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The CI/CD example automatically commits and pushes generated documentation changes to the repository without an explicit warning about automated modification. In practice, this can enable unreviewed content changes on main branches, amplify mistakes from generation logic, and create a path for persistence if upstream inputs influence generated docs.

Content

No source excerpt is available for this finding.