ClawHub
Back to skill

Security audit

Process Keeper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain documentation helper that reads project context and writes process notes, with no code execution, network access, or hidden behavior found.

Install this only if you want your agent to inspect repository history and create or update process documentation. For sensitive projects, review generated notes before sharing them publicly and prefer explicit invocation when you do not want automatic process-log updates.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrases are generic natural-language requests such as 'Record this decision' and 'Turn this into a retrospective', which can overlap with ordinary conversation and cause the skill to activate when the user did not explicitly intend to invoke it. In a repo-aware agent, unintended invocation can lead to unnecessary repository inspection, timeline reconstruction from commits/files, and creation of process-note artifacts, increasing the chance of unintended data exposure or file modifications.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill enables implicit invocation but does not provide a narrowly scoped activation description or constraints, which can cause the agent to invoke it in unintended contexts. Because this skill writes project history and process documentation, accidental invocation could lead to unauthorized summarization, modification, or disclosure of development context and internal decisions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The markdown states that if no process notes exist yet, the skill should create docs/process/, which affects repository contents. The README does not clearly warn users that the skill may create files or directories in their project when used.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The example explicitly tells the agent to append a new entry in docs/process/HISTORY.md, which normalizes making repository file modifications without any confirmation or safety framing. In an agent skill focused on documenting project history, this is contextually plausible, but it still creates a real risk of unintended file writes if the system executing the skill treats examples as acceptable default behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.