ClawHub
Back to skill

Security audit

Dev Progress Governor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow project-progress helper that may update a progress log, but it does not include hidden code, credential access, network behavior, or system persistence.

Before installing, understand that the skill is meant to help decide whether work is ready to commit and to draft or append progress-log entries. Review any proposed progress-log write or commit message before accepting it, especially if you use a different log path or commit convention.

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 manifest description says to use the skill when the user wants help 'summarizing completed steps' or 'tracking blockers,' alongside several other open-ended project-support tasks. While some phrases are specific, the overall trigger guidance is broad and lacks explicit exclusion examples or narrow invocation constraints, which could cause unintended activation during ordinary software-help conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.