ClawHub
Back to skill

Security audit

skill-graph-audit

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives coherent instructions for auditing skill dependency graphs and does not show hidden, destructive, persistent, or data-exfiltrating behavior.

Review that the referenced skill_graph.py script comes from the intended source before running it, since this package documents the workflow but does not include the implementation. The skill itself is low-risk markdown guidance for local graph auditing.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · modules/interpretation.md (reported line 60)May include surrounding context.

md
|-------|----------------|
| bugs | Fix in the same PR; do not merge with bugs > 0 |
| external | Confirm external plugin is documented in plugin.json |
| placeholders | Annotate with `<!-- template -->` to suppress |

## Cross-Plugin Coupling

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest trigger auditing skills is a short natural-language phrase without additional scope constraints, negative examples, or context limiting when this skill should activate. Because it is broad and could match ordinary discussion about reviewing skills in general, it risks unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.