ClawHub
Back to skill

Security audit

ship-it

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only operational readiness checklist that asks for scope, inspects project evidence, and explicitly avoids editing code without approval.

Install this when you want a structured operational release gate. Expect the agent to inspect relevant repo files and ask for scope; use a normal code-review skill instead for diff quality, tests, dead code, or refactoring feedback.

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

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advertises very broad activation phrases such as 'is this ready to ship?' and 'asks whether a release is operationally safe,' which are common conversational requests and may match user intent imprecisely. This can cause unintended invocation of the skill in contexts where the user wanted a lighter review or a different workflow, potentially leading the agent to over-collect repo context or produce authoritative release-readiness judgments without the user explicitly selecting this audit.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The invocation examples include ambiguous, everyday release questions like 'can we deploy this?' and 'anything missing before we ship?' without sufficiently strict constraints. In practice this increases the chance of the skill being auto-selected when the user's intent is unclear, which can create mis-scoped security or operational assessments and reduce user control over what repo inspection actions are taken.

Content

No source excerpt is available for this finding.