ClawHub
Back to skill

Security audit

Obsidian Daily

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Obsidian note helper, but its shell command templates can unsafely mix user-provided text into commands and its manifest contains unresolved merge-conflict markers.

Review this skill before installing. Its Obsidian behavior is expected, but avoid letting an agent paste arbitrary journal entries, search terms, vault names, or paths directly into the provided shell templates. The publisher should fix the merge-conflict markers and document safe argument passing before broad use.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:71
Finding

Shell Command Injection Through Unsafe User-Input Substitution

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill provides concrete commands that create and append to Obsidian vault files without explicitly warning that these operations modify user data. In an agent-executed context, this can cause unintended file changes, note pollution, or accidental overwrites/appends if the user expected a read-only action.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.