Back to skill

Security audit

peter-ci-gate

Security checks for vulnerabilities and agentic risk

Overview

This CI helper is mostly coherent, but it can automatically rerun GitHub Actions workflows without clearly asking the user first.

Install only if you are comfortable with the skill using your GitHub CLI session to inspect PR checks and potentially rerun a workflow. Before use, prefer requiring the agent to show the flaky-failure evidence and ask before any gh run rerun command.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad, everyday requests like checking CI or whether something can merge, which increases the chance the skill is invoked in situations the user did not explicitly intend. Because this skill can progress from passive inspection to taking a remote action (gh run rerun), accidental invocation could cause unauthorized or surprising CI reruns and misleading gate decisions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill authorizes a remote CI rerun as part of the default handling strategy for flaky failures without requiring a prior warning or confirmation from the user. This is dangerous because rerunning workflows is a state-changing external action that can consume CI resources, alter audit trails, and violate user expectations if performed automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description specifies output as “是否可合并” and the entire skill content is written as if Chinese is the required interaction language, with no opt-in or alternative locale described. This can violate language/locale policy when the user has not explicitly chosen Chinese.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.