ClawHub
Back to skill

Security audit

Work Receipt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation helper that summarizes local coding work; it has privacy considerations but no hidden execution, network use, persistence, or destructive behavior in the inspected artifact.

Install only if you are comfortable with the agent summarizing local repository activity, diffs, TODOs, tests, and relevant command context. Use it intentionally, and redact or avoid including secrets, credentials, confidential paths, or unrelated terminal history in generated receipts.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly states it analyzes git history, file changes, test results, terminal commands, and filesystem artifacts, but the description does not clearly warn users that potentially sensitive local activity and command history may be inspected. In practice, this can lead to unanticipated exposure of secrets, internal paths, credentials typed into terminals, or confidential project details in generated summaries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The 'When to Invoke' section uses broad conditions such as 'End of every work session,' 'Before standup,' and 'Before creating a PR' without defining clear boundaries, required context, or exclusions. In a markdown skill description, this can create ambiguous activation scope and increase the chance of unintended invocation during ordinary workflow conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.