Security audit

Commit Message Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides commit and PR wording guidance, with a minor note that it asks the agent to remember lightweight usage categories over time.

This appears safe to install for commit-message help. Be aware that it may try to keep simple counts of whether prior inputs were diffs, descriptions, or snippets; avoid relying on that behavior for private analytics, and paste only code or diffs you are comfortable sharing with the agent.

A.I.G

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

Findings (1)

T01 · Skill Instruction Hijacking

Note

Location: SKILL.md:104
Finding: Undisclosed Cross-Invocation Tracking and Output Manipulation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger 'Any git diff or code change needing a message' is broad and lacks boundaries or exclusion conditions. In a markdown skill description, this can cause unintended invocation because many ordinary development conversations involve code changes without explicitly requesting this skill.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.