Security audit

pr-description

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple read-only PR description helper with no hidden execution, persistence, or data exfiltration behavior found.

Install this if you want help drafting PR descriptions from local branch diffs. Be aware it will read and summarize code changes in the repository, and the trigger wording is broad enough that you may want to invoke it only when you specifically want a PR or merge-request summary.

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

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description says to use the skill when the user asks for a PR description, a merge request summary, or 'what does this change do'. That last phrase is very general and could match many ordinary coding conversations outside the intended pull-request context, increasing the chance of unintended invocation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.