ClawHub
Back to skill

Security audit

Phy Http Cache Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward HTTP cache-header audit helper that uses curl on user-provided URLs and does not install code, persist changes, or hide unrelated behavior.

Install only if you want an agent to fetch response headers for URLs you provide. Avoid pointing it at private admin endpoints, localhost services, or third-party systems unless you have permission and understand that curl will make live network requests.

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
95% confidence
Finding

The skill explicitly supports live requests to arbitrary URLs and localhost services using curl, but it does not warn users that invoking it will contact external systems or local development endpoints. This creates a real risk of unintended network access, including probing internal services on localhost or sending requests to sensitive third-party endpoints, which can have SSRF-like effects in agent environments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes phrases such as "cache issues", "Last-Modified", and "cache hit rate", which are generic enough to appear in normal conversation or unrelated troubleshooting. The skill does not provide exclusion conditions or negative examples to clarify when these phrases should or should not invoke the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.