ClawHub
Back to skill

Security audit

clawlite-retro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Git retrospective helper; its main risk is that it fetches from the repository remote when used.

Before using this skill, be comfortable with it contacting the repository's origin remote via git fetch and reading local Git author names/emails, commit history, file-change summaries, and TODOS.md. It appears appropriate for a repository where retrospective analysis is expected.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs git fetch origin <default> --quiet, which performs network access to a remote repository without any user notice, consent, or gating. Even though git fetch is a common developer operation, in an agent skill this can disclose repository metadata to the remote, trigger credential use, and violate expectations in offline or restricted environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.