Back to skill

Security audit

Feature Retcon / 需求后悔药

Security checks for vulnerabilities and agentic risk

Overview

This skill is a controlled local workflow for revising project decisions after user confirmation, with no evidence of hidden network, persistence, or exfiltration behavior.

Before installing, use it only for repositories where you want an agent to coordinate staged project edits. Review the initial read-only assessment carefully, confirm writable roots and deletion lists narrowly, and do not allow sensitive or large recovery payloads unless you accept that the local contract may contain those original bytes until it is closed or restored.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (11)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill explicitly instructs use of shell commands and file operations, including Python script execution and state-changing workflow steps, but it declares no tool scope or permission boundaries. This creates an authorization ambiguity where an agent may execute higher-risk capabilities than the skill metadata communicates, increasing the chance of unintended file modification or command execution in the wrong context.

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 all operational guidance force a specific language/locale for users and operators. Under the stated policy, a skill should not mandate a specific language unless it offers user choice or clearly documents a justified locale-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document title and instructions are presented entirely in Chinese, and the file does not indicate that use of Chinese is optional or limited to a region-specific workflow. This can violate a language/locale policy when users are not given an explicit choice of language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The entire assessment workflow and required output structure are specified only in Chinese, with no indication that users may choose another language or locale. This can violate language/locale policy requirements when a skill imposes a specific language without explicit opt-in or documented regional justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file presents all skill-related guidance and examples exclusively in Chinese. Under the policy rule for natural-language violations, forcing a specific language without user opt-in or justification can exclude users and constitutes a locale/language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is entirely written in Chinese and contains operational instructions, command guidance, and safety-relevant workflow requirements without indicating that language selection is optional. Under the policy rule for natural-language constraints, this constitutes a locale/language restriction because users are not offered an opt-in choice or documented alternative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains all user-facing instructions in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. That creates a natural-language policy concern because it effectively forces a specific language without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file contains all user-facing instructional content in Chinese and does not indicate that language selection is optional or user-configurable. 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.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/contract.py (reported line 256)May include surrounding context.

python
def run_git(repo_hint: Path, *args: str, check: bool = True) -> subprocess.CompletedProcess[bytes]:
    try:
        result = subprocess.run(
            ["git", "-C", str(repo_hint), *args],
            stdout=subprocess.PIPE,
            stderr=subprocess.PIPE,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file's instructional content is entirely in Chinese, which can amount to a language policy violation when a skill forces a specific language without user opt-in. There is no indication that the skill is region-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

This code file contains natural-language descriptions and error/help text in Chinese, starting with the module docstring. Under the locale policy rule, forcing a specific language without user opt-in is a policy violation unless the locale constraint is explicitly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.