ClawHub
Back to skill

Security audit

Autoselect Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed helper that recommends which other skills to load, with no hidden code, network access, destructive behavior, or credential handling found.

Install this only if you want the agent to use a meta-helper that may suggest loading other skills automatically. Review the trigger breadth if you prefer manual skill loading only, but the inspected artifact does not show hidden execution, exfiltration, destructive actions, or unsafe persistence.

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 (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

md
Drop `SKILL.md` into your agent's skills directory. For Mavis-format agents, that is

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest defines multiple broad automatic triggers, including generic keyword matching and heuristics based on intent overlap. In a skill-loading system, this can cause the skill to run in many unrelated conversations, increasing unnecessary context loading and the chance of unintended follow-on skill invocations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The auto-trigger guidance relies on ambiguous concepts like domain specificity, workflow class, and tool-name overlap, which are underspecified and likely to match benign user text too often. In context, this makes the skill more dangerous because it is designed to influence which other skills get loaded, so over-triggering can cascade into broader prompt/context expansion.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.

md
## Install

Drop `SKILL.md` into your agent's skills directory. For Mavis-format agents, that is
`$AGENT_HOME/.skills/autoselect-skill/SKILL.md`. Restart the agent so the new skill is
picked up by the skill loader.

## License