Back to skill

Security audit

Chinese Calendar Cn

Security checks for vulnerabilities and agentic risk

Overview

The package does not show data theft or persistence, but it is advertised as a Chinese lunar calendar tool while its script only prints unrelated generic guidance.

Review before installing. The artifact appears low-risk for system access, but it is not reliable for its advertised purpose; install only if you are comfortable with a placeholder-style Bash reference script, or ask the publisher to align the script and documentation with real Chinese calendar functionality.

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
  • 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 date and astrology-related capabilities. The supplied code does not implement any of these features. Instead, it is a static Bash reference script that outputs generic instructional content and help text. There is no logic for calendar data, date conversion, zodiac mapping, festival lookup, or any Chinese calendar computation. This is a clear description-behavior mismatch with a materially different primary 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 and help text claim Chinese lunar calendar capabilities, but the script only emits generic static guidance and performs no calendar computation, conversion, festival lookup, or related functions. This is dangerous because users and higher-level agents may rely on false capability claims, leading to incorrect task delegation, silent failure, or trust abuse in automation pipelines.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The inline description presents the tool as a Chinese calendar reference utility, but nearly all embedded content is generic process advice unrelated to the stated domain. This mismatch can mislead users and orchestrating agents into selecting the skill for unsuitable tasks, weakening system reliability and creating an avenue for deceptive packaging.

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
92% confidence
Finding

The markdown states that all commands output plain-text reference documentation in Chinese. This imposes a specific language behavior without indicating user opt-in or presenting it as a necessary region-specific constraint, which matches the locale-policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The top-level description says the tool is for working with "chinese calendar cn," which hard-codes a Chinese/China locale context in the skill's natural-language description. There is no indication that users can choose another language or locale, nor any justification that the tool is intentionally region-specific for compliance or other documented reasons.

Content

No source excerpt is available for this finding.