Back to skill

Security audit

Version Decider

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed SemVer version-recommendation skill that reads local version information and runs its bundled Python calculator without network access or persistence.

Before installing, be comfortable with the skill reading local project version metadata and running its bundled Python calculator. Keep its execution to the documented read-only workflow, do not grant write/network/package-install permissions for this skill, and review the final version recommendation before publishing a release.

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 (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose describes a release-decision skill whose primary function is to determine the next SemVer version from code changes. The actual code does something entirely different: it parses a markdown file, extracts frontmatter fields like description and when_to_use, estimates token counts, and reports documentation budget/compliance information. The module docstring explicitly states it is a dev/maintenance-only tool and not part of the runtime decision flow, even naming another file as the decision engine. This is a material purpose mismatch, not a mere implementation detail.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
- This skill's `SKILL.md` and `references/` are **English by default** (ClawHub Natural Language Policy: English default).

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
55% confidence
Finding

The skill uses 'file_write' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JSON file defines all user-facing strings exclusively in Chinese, which indicates the skill can present output in a fixed language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file is a Chinese-localized variant and presents its content entirely in Chinese while identifying itself as a localized mirror. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue when no user choice is offered in the file itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file explicitly states that measure_skill.py user-facing print output is still entirely in Chinese. A skill forcing a specific language for user-visible output without offering a choice or opt-in matches the natural-language locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Line L003 says the Chinese file is only an optional mirror and that the English version is the default/authoritative one. This introduces a language-priority policy in the documentation rather than presenting languages as equal options, which can be read as forcing a specific language absent explicit user opt-in.

Content

No source excerpt is available for this finding.