Back to skill

Security audit

Deep Work Planner

Security checks for vulnerabilities and agentic risk

Overview

The skill is a prompt-only productivity planner with an installation caution but no evidence of hidden data access, execution, or persistence.

This appears safe to use as a prompt-only planning helper. Before installing, consider using a pinned or trusted version of the installer if your environment requires strict supply-chain controls, and avoid putting highly sensitive task details into any assistant unless that fits your own privacy expectations.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
README.md:36
Finding
Unpinned Package Execution in Installation Instructions## Vulnerability Details **File Location**: `README.md`, line 36 **Vulnerability Type**: Unpinned third-party package execution **Risk Level**: Medium **Complete Code Snippet**: ```bash npx clawhub install tetsuakira-vk/deep-work-planner ``` ### Technical Analysis The documented installation command invokes `clawhub` through `npx` without specifying an exact package version or integrity value. If the package is not already installed locally, `npx` may resolve and execute a mutable version from the configured npm registry. Consequently, the code executed during installation is not fully represented by or auditable from this repository. This creates a supply-chain trust boundary: compromise of the package, its dependencies, its registry account, or the registry resolution process could cause users following the documentation to execute altered code. The mutable skill identifier passed to the installer may introduce an additional unpinned retrieval step, depending on the behavior of the external `clawhub` tool. No evidence in the audited files demonstrates that the current `clawhub` package is malicious. The issue is the lack of version and integrity controls around executable third-party content. ### Attack Path 1. An attacker compromises the publisher account, package, dependency chain, or registry source used to resolve `clawhub`. 2. The attacker publishes or causes resolution of a modified package version containing malicious CLI or lifecycle behavior. 3. A user copies the installation command from `README.md`. 4. `npx` downloads and executes the mutable package version. 5. The malicious code runs with the permissions and environmental access of the invoking user. ### Impact Assessment Successful exploitation could provide access equivalent to the user running the installation command. Depending on that user's permissions and environment, malicious package code could read or modify accessible files, inspect enviro ...[truncated 421 chars]
Remediation
## Remediation Suggestions 1. Pin `clawhub` to a reviewed exact version rather than allowing `npx` to resolve a mutable release: ```bash npx --yes clawhub@<verified-exact-version> install tetsuakira-vk/deep-work-planner ``` 2. Pin the installed skill to an immutable version, commit, or content digest if the installer supports this capability. 3. Document the expected registry and official package provenance so users can verify that the package has not been obtained from an unexpected source. 4. Publish and verify integrity hashes or signed release artifacts for both the installer and skill package. 5. Recommend installation under a non-privileged account and explicitly warn users not to run the command with `sudo` or administrative privileges. 6. Where practical, provide a non-executing download and verification workflow so users can inspect the resolved package before running it.
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 (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding
The README instructs users to execute `npx clawhub install ...` without pinning a specific version of the package being invoked. That creates a supply-chain risk: users may fetch and run whatever version is current at install time, including a compromised or malicious update, and `npx` execution can result in code being run on the user's machine.

Vague Triggers

Low
Confidence
83% confidence
Finding
Because this is a markdown file, vague-trigger review applies. The phrase "Anyone who ends the day having been 'busy' but not productive" is extremely broad and does not define a clear activation boundary, increasing the risk that the skill could be invoked for generic productivity conversations rather than a narrow scheduling use case.

Static analysis

No suspicious patterns detected.