Security audit

Document Diff

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: compares user-chosen files and reports differences, with minor cautions about output language and safe path handling.

Before installing, expect this skill to inspect the two files or directories you ask it to compare and to produce its report in Chinese. Use it only with files you intend the agent to read, and prefer agents or workflows that pass file paths safely rather than concatenating raw paths into shell commands.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:23
Finding: User-Controlled File Paths May Enable Shell Command or Argument Injection
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest description says to use the skill when the user asks to compare files, find differences between documents, generate a diff report, or check what changed between two versions. These are broad natural-language triggers and the file does not provide exclusion conditions or tighter constraints, which could cause the skill to match ordinary comparison requests more broadly than intended.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill says it will generate a structured difference report in Chinese, and later reiterates that the report should be presented in Chinese. This imposes a language constraint without user opt-in, which is a natural-language policy violation under the locale-choice rule.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The instruction to present the report in Chinese with clear sections is a hard-coded locale requirement. Because the file does not provide an opt-in mechanism or a documented justification for restricting output to Chinese, it conflicts with the language/locale policy.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The note says to explain what changed in plain Chinese after showing diff output. This repeats the same mandatory language requirement without any user choice or documented regional justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.