ClawHub
Back to skill

Security audit

GitHub Actions Failure Spike Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local reporting tool that reads GitHub Actions run JSON files and reports failure-rate spikes without hidden network, persistence, or destructive behavior.

Install this if you want a local GitHub Actions failure-spike report. Run it against a narrow artifacts/github-actions path or explicit fixture directory, and avoid broad globs that could accidentally include unrelated JSON files in the report output.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill reads local GitHub Actions JSON artifacts but does not declare any explicit tool scope such as permissions or allowed-tools. Even though the documented behavior is limited to local file reads, the absence of a scope declaration weakens least-privilege guarantees and can allow broader-than-intended file access when the skill is executed in an agent environment.

Static analysis

No suspicious patterns detected.