Security audit

Code Analysis Toolkit Free

Security checks for vulnerabilities and agentic risk

Overview

The skill is a personal Git history analysis helper, but its install and run instructions are incomplete and could execute an unverified local Python module.

Review this skill carefully before installing. Only use it in an isolated environment on repositories you own or have explicit consent to analyze, pin and verify dependencies yourself, and do not run `python -m src.main` unless you have a trusted implementation package installed and know exactly which file Python will execute.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:181
Finding: Unpinned Third-Party Dependencies Create a Supply-Chain Risk
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:195
Finding: Documented Command May Resolve and Execute an Unrelated Python Module
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (5)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The manifest description is written in Chinese, and the document consistently presents the skill interface and usage guidance only in Chinese. There is no indication that the skill supports user language choice or that this locale restriction is required for a region-specific compliance purpose.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The display name and surrounding user-facing content are presented exclusively in Chinese, which imposes a language choice on users. The file does not mention alternative language support, user selection, or a justified regional limitation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger condition is broad enough to match generic analysis, reporting, or visualization requests, increasing the chance the agent invokes this skill in contexts the user did not intend. In practice, that can cause unnecessary repository inspection or execution of local analysis commands on sensitive codebases.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill makes strong privacy claims that it runs fully locally and does not transmit data externally, yet it also declares an external LLM API as required. This contradiction can mislead users into exposing repository metadata or report contents under false assumptions about data locality and confidentiality.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 71% confidence
Finding: L306-L308 state that --i-have-consent is a hard gate and that the tool exits without it, but this file contains only documentation and command examples, not code implementing that guarantee. For an MD+EXEC skill, presenting this as an enforced safeguard contradicts the actual material here, which cannot itself ensure the restriction.
Content: No source excerpt is available for this finding.