Back to skill

Security audit

github-project-radar

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language workflow for evaluating GitHub repository candidates, with no hidden execution, credential handling, persistence, or destructive behavior found.

Install this if you want a Chinese-language process for tracking GitHub repository candidates. Review the candidate table path before allowing write-back, and require explicit confirmation before any repository installation test, as the skill itself recommends.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description explicitly states this is a '中文评估流程', which imposes a specific language requirement in the natural-language skill policy. The file does not indicate that users may choose another language or opt in to Chinese output, so it can violate language/locale choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The entire checklist is written in Chinese and provides no indication that language selection is optional or that the skill is intended only for a Chinese-speaking or region-specific context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The phrase '本项目以"国内创作者能直接用"为目标' expresses a natural-language locale constraint aimed at a specific regional audience. Under the policy, forcing or presuming a specific language/locale without opt-in can be a violation unless the regional limitation is explicitly justified as inherent to the tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file title and example content require Chinese text, such as the header 'GitHub 候选表' and Chinese guidance in table cells. This imposes a specific language/locale on users without offering opt-in or documenting a justified region-specific need, which matches the language-policy concern for natural-language content.

Content

No source excerpt is available for this finding.