Security audit

split-to-prs

Security checks for vulnerabilities and agentic risk

Overview

This skill gives an agent a cautious workflow for splitting repository changes into reviewable pull requests, with user approval required before making branches, commits, pushes, or PRs.

Before installing, understand that this skill is meant for repositories and can lead the agent to create branches, commits, pushes, and pull requests after you approve a split plan. Review the proposed slices carefully before approving execution.

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

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: 91% confidence
Finding: The manifest says to use the skill when the user asks to split "a chat, set of changes, branch, or PR." Terms like "split a chat" and "set of changes" are broad and ambiguous, and the file does not provide tighter trigger constraints or negative examples to limit invocation scope.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.