ClawHub
Back to skill

Security audit

Phy Pr Size Splitter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PR-size analysis helper that uses local git and GitHub CLI context, with no evidence of hidden persistence, exfiltration, or destructive automatic behavior.

Install only if you are comfortable with the agent inspecting the current repository or specified GitHub PR through git and gh. Use explicit invocations like /pr-size and review any generated git, gh pr create, or PR-comment actions before allowing them to run or be posted.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill advertises broad natural-language triggers such as 'review this diff' and 'atomic commits' in metadata, which could cause the agent to invoke this skill during ordinary development conversation rather than only when the user explicitly wants PR-size analysis. Unintended activation can lead to unexpected execution of local gh/git commands against the current repository context and disclosure of repository structure or diff metadata in the response.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger section repeats ambiguous activators like 'split this PR', 'review this diff', and 'how do I split this' without exclusion conditions, increasing the chance of accidental routing from routine chat into a command-capable skill. In this skill's context, accidental activation is more concerning because subsequent steps instruct use of local repository tooling (gh, git) and may surface sensitive branch, file, or PR information the user did not intend to analyze.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.