ClawHub
Back to skill

Security audit

CI Pipeline Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill statically reviews CI configuration files and Dockerfiles to suggest pipeline speedups, with no evidence of hidden execution, persistence, credential access, or data exfiltration.

Before installing, expect the skill to inspect CI workflow files and Dockerfiles in the repository. Treat generated YAML as a suggestion to review before applying, and avoid providing CI logs unless you explicitly want log-based analysis despite the documentation inconsistency.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger guidance uses broad natural-language phrases like 'CI is too slow' and 'optimize our pipeline,' which can cause the skill to activate in contexts where the user did not intend repository-wide workflow analysis. In an agent setting, over-broad activation increases the chance of unnecessary access to CI configuration files and generation of workflow modifications that affect build and deployment behavior.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest description explicitly scopes the skill to analyzing GitHub Actions, GitLab CI, and CircleCI pipelines. However, the documented behavior includes detection and support for Jenkins, Bitbucket Pipelines, and Azure DevOps, which expands the analyzed platforms beyond the stated scope.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The timeline section states 'Parse CI logs or config to estimate job duration,' which asserts log access as part of behavior. Later, the notes explicitly say 'Does not access CI logs or run history — analyzes config files statically,' which directly contradicts that earlier documentation.

Static analysis

No suspicious patterns detected.