ClawHub
Back to skill

Security audit

Release Prep

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Python release-preparation helper whose file changes and publishing steps are disclosed and aligned with its stated purpose, though users should invoke write and publish modes deliberately.

Install this if you want an agent-assisted Python package release workflow. Use audit mode for read-only checks, and only ask for fix or release mode when you are comfortable with repository edits, changelog/version updates, local commits/tags, and a PyPI publish step that should require explicit confirmation.

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
  • 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad enough to match common requests like 'publish', 'release', or 'check docs', which can cause this skill to activate in situations where the user did not intend a high-impact release workflow. Because the skill includes file modification, version bumping, tagging, and publishing steps, over-triggering materially increases the risk of unintended repository changes or release actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises that it can auto-fix issues but does not immediately warn that it may modify repository files, create commits/tags, or prepare artifacts. Users may invoke it expecting analysis only, while later phases enable write operations that can alter code, docs, changelogs, and version metadata.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.