Security audit

OC PR Review

Security checks for vulnerabilities and agentic risk

Overview

This PR review skill is coherent and purpose-aligned, with disclosed GitHub and optional Feishu actions, but users should treat publishing reviews or notifications as external sharing.

Install only if you are comfortable giving the agent access to authenticated GitHub PR data. Ask it to draft reports first, and require confirmation before posting GitHub reviews/comments or sending Feishu messages, especially for private repositories or security findings.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill instructs the agent to send PR review summaries to Feishu without an explicit consent/confirmation step or warning that repository metadata, code-review findings, and possibly sensitive internal details may be transmitted to an external service. In a PR review context, review content can easily contain confidential code paths, vulnerability details, usernames, branch names, and internal project information, so silent or weakly-signaled exfiltration is risky.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill provides commands for submitting PR reviews and line comments directly to GitHub, but does not clearly warn that these actions modify external state on the user's behalf. This can cause unintended approvals, requests for changes, or publication of sensitive review text to collaborators, which is especially risky in a workflow that also analyzes security issues and may expose internal findings publicly within the repository context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The manifest description, headings, instructions, and user-facing templates are written entirely in Chinese, and the skill does not state that language is configurable or based on user preference. This is a natural-language policy concern because it effectively imposes a specific language without documented opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.