ClawHub
Back to skill

Security audit

Phy Async Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill reads source files to report async error-handling issues and does not show evidence of sending data, changing files, or persisting itself.

Install only if you are comfortable letting the skill run a local Python static scan over source files in the current project. Review its findings before applying suggested fixes; the inspected artifact reports issues but does not modify code itself.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The invocation example "Check my codebase for unhandled async errors" is natural language that overlaps with ordinary requests a user might make during general coding help. The file does not provide exclusion conditions or tighter activation boundaries beyond examples, so the skill could be invoked unintentionally.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The phrase "Why is my Express server silently dying on async routes?" reads like a general support question rather than a narrowly scoped trigger. Without explicit wording that only this exact command or slash-command context activates the skill, it risks accidental invocation during normal conversation.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
line=i + 1,
            severity='HIGH',
            description=(
                'Goroutine calls error-returning functions without checking errors. '
                'Errors inside goroutines do not propagate to the caller — they are silently ignored.'
            ),
            matched_text=line.strip()[:120],
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.