Back to skill

Security audit

analyze-ci

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow GitHub Actions failure analyzer that uses a GitHub token and CI logs for its stated purpose, with no evidence of hidden persistence or destructive behavior.

Install only if you are comfortable letting the skill access GitHub Actions logs for the target repositories and analyze them with Claude. Use a least-privilege GitHub token, avoid running debug output in shared logs, and treat returned log snippets as potentially sensitive.

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
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly relies on GitHub credentials and advertises a debug mode that reveals "tokens and costs," but it does not provide a clear warning about secret exposure, redaction behavior, or safe handling of logs and output. In a CI-analysis context, this is risky because users may run the skill in shared terminals, capture output into logs, or paste results elsewhere, potentially disclosing sensitive authentication material or other secrets surfaced from CI logs.

Content

No source excerpt is available for this finding.