ClawHub
Back to skill

Security audit

SRS Support

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-oriented SRS support helper with no hidden execution, persistence, or credential handling found.

Install this if you want SRS-specific operational help. Be aware that its trigger wording is broad, so for non-SRS streaming questions you may want to explicitly name the intended technology to avoid routing confusion.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description has very broad activation criteria ('use when anyone asks about SRS...') that can cause over-invocation on ordinary media-server or streaming questions, even when a narrower or more appropriate skill should respond. In an agent system, ambiguous routing can expose users to irrelevant instructions, unnecessary repository context loading, or incorrect authoritative answers outside the intended support boundary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.