ClawHub
Back to skill

Security audit

Chinese Calendar Cn

Security checks for vulnerabilities and agentic risk

Overview

The skill is not destructive or credential-seeking, but its advertised Chinese calendar commands do not match the bundled executable, which only prints generic placeholder guidance.

Review before installing because the package does not appear to provide the Chinese calendar functionality it advertises. It does not show signs of credential theft, persistence, or destructive behavior, but users should not rely on it for calendar conversion, auspicious-date selection, or culturally date-sensitive automation unless the implementation is corrected.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description promises a functional Chinese lunar calendar tool with specific calendar-related capabilities. The code instead implements a simple shell-based reference manual that outputs canned, generic instructional text. None of the promised calendar features are present, and the primary purpose is materially different from the declaration. There are no suspicious extra permissions or resource accesses, but the core behavior does not match the stated purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill metadata promises Chinese lunar calendar features such as solar terms, zodiac years, auspicious dates, festivals, stems/branches, and calendar conversion, but the script only emits generic placeholder reference text. This is a supply-chain integrity issue: users or downstream agents may rely on functionality that does not exist, leading to incorrect automation decisions, silent task failure, or misplaced trust in the package.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation states that all commands output plain-text reference documentation in Chinese. This imposes a specific language behavior without indicating any user choice, opt-in, or justified locale restriction, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The embedded content is generic boilerplate and unrelated to the claimed Chinese calendar domain, indicating deceptive or low-integrity packaging. In an agent skill ecosystem, this can mislead users into invoking the skill for culturally or date-sensitive tasks and can mask future malicious substitutions because the package already normalizes mismatch between claim and behavior.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · scripts/script.sh (reported line 152)May include surrounding context.

sh
1. **Skipping planning**: Jumping in without understanding requirements
2. **Ignoring documentation**: Not recording decisions and changes
3. **Over-complicating**: Adding unnecessary complexity
4. **Skipping tests**: Deploying without verification
5. **Working in isolation**: Not seeking feedback or review

## How to Avoid Them

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file description explicitly frames the tool as "chinese-calendar-cn" and repeatedly uses the China-specific/Chinese locale marker "cn" without any user opt-in or alternative locale handling. Under the language/locale policy, forcing a specific locale is a natural-language policy concern unless the constraint is clearly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.