Back to skill

Security audit

github-health-diagnosis

Security checks for vulnerabilities and agentic risk

Overview

The skill appears purpose-built for GitHub health reports, but it automatically publishes repository and security-review results to Feishu Wiki without a required publish confirmation or destination.

Review this before installing if you work with private, internal, or due-diligence repositories. Only use it when the resulting report may be shared to Feishu Wiki, and prefer specifying an explicit Wiki space and parent location. A safer version would require explicit confirmation before publishing and offer a local preview/redaction mode.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The workflow explicitly ends by publishing the generated diagnosis to Feishu Wiki, but the user-facing description does not prominently warn that analysis results will be automatically shared to an external documentation system. This creates a meaningful risk of unintended disclosure of repository details, findings, or potentially sensitive internal context, especially for private or due-diligence use cases.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly describes publishing repository diagnostic results to Feishu Wiki, but it does not warn users that potentially sensitive repository metadata, code-review outputs, issue/PR summaries, and security findings may be transmitted to an external third-party platform. In a security-analysis workflow, silent external publication increases the risk of unintended data disclosure, especially when scanning private, internal, or pre-release repositories.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad natural-language phrases such as '帮我看看这个GitHub项目的质量' and '这个项目代码质量怎么样', which are plausible in ordinary conversation and could invoke the skill unintentionally. Because this skill performs multi-step analysis and publishes results externally, accidental activation could cause unwanted data processing and report generation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This workflow performs an external side effect by creating a Feishu Wiki page, but the description and input schema do not clearly gate publication behind an explicit publish/confirm flag or tightly scoped destination requirements. In practice, a user supplying only a repository can trigger content generation and potential publication into a default Wiki space, which increases the risk of unintended data dissemination, spam, or posting analysis of sensitive/private repositories to the wrong destination.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and multiple user-facing labels are written in Chinese, including health rating labels and field descriptions, but there is no indication that the skill is China-specific or that users can opt into another language. That creates a locale policy concern because the skill appears to impose a specific language by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

All user-facing instructions, examples, and output descriptions in the file are presented only in Chinese, and there is no indication that the user can choose another language. This can violate a language/locale policy when a skill effectively forces a specific language without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

All user-facing instructions, triggers, labels, and examples are presented only in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.