Back to skill

Security audit

The Founders Playbook

Security checks for vulnerabilities and agentic risk

Overview

This is a content-only startup guidance skill with ordinary install cautions, not evidence of malicious behavior.

Review the package source before installing and prefer a pinned or trusted installer version when possible. Once installed, this skill should only provide startup-stage guidance; confirm the stage if the agent applies it during an unrelated conversation.

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 (2)

T08 · Insecure Dependencies

Warning
Location
README.md:15
Finding

Unpinned npm CLI Packages Executed Through npx in README

Content
View full analysis

Vulnerability Details

File Location: README.md:15-20
Vulnerability Type: Unpinned third-party dependency execution
Risk Level: Medium

Vulnerable Code

bash
# Install via ClawHub
npx clawhub install the-founders-playbook

# Or install via skills.sh (any agent)
npx skills add casvian/the-founders-playbook

Technical Analysis

The documented installation commands invoke third-party npm CLI packages through npx without specifying reviewed package versions or integrity hashes. When the packages are not already available locally, npx can retrieve their current versions from the configured npm registry and immediately execute them.

Consequently, the effective code executed by these commands can change after this repository has been reviewed. The repository does not provide a lockfile, checksum, signature-verification procedure, or other mechanism that binds these commands to known-good package artifacts.

This is a supply-chain weakness rather than evidence that the named packages are currently malicious. Exploitation would require compromise or malicious publication of a package version, registry resolution, or another relevant part of the dependency-delivery chain.

Attack Path

  1. An attacker compromises a package maintainer or registry account, takes control of a referenced package, or otherwise causes a malicious version to be resolved.
  2. The attacker publishes a version containing malicious CLI or lifecycle behavior.
  3. A user copies one of the installation commands from README.md.
  4. npx resolves and downloads the unpinned package version from the configured registry.
  5. The malicious package executes under the account and environment of the user running the command.
  6. The payload can access resources available to that user and may modify files or launch additional processes, subject to operating-system controls.

Impact Assessment

Successful exploitation could result in arbitrary code execution with the pr ...[truncated 503 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin each CLI to a specifically reviewed version, for example:

    bash
    npx --yes clawhub@<reviewed-version> install the-founders-playbook
    npx --yes skills@<reviewed-version> add casvian/the-founders-playbook
    
  2. Replace the placeholders only with versions whose source, package metadata, and published artifacts have been reviewed.

  3. Document the expected package registry and verified publisher identity.

  4. Publish cryptographic checksums or signature-verification instructions where the distribution system supports them.

  5. Prefer a lockfile-backed installation workflow or a locally installed, version-pinned CLI over automatic execution of the latest registry release.

  6. Recommend running installation with a non-privileged account and in an isolated environment.

  7. Periodically review pinned versions and update them through an explicit security-controlled process rather than resolving an unrestricted latest version.

T08 · Insecure Dependencies

Warning
Location
setup.md:32
Finding

Unpinned npm CLI Packages Executed Through npx in Setup Guide

Content
View full analysis

Vulnerability Details

File Location: setup.md:32-37
Vulnerability Type: Unpinned third-party dependency execution
Risk Level: Medium

Vulnerable Code

bash
# Via ClawHub (any OpenClaw agent)
npx clawhub install the-founders-playbook

# Via skills.sh (any agent — Claude Code, Cursor, Copilot, Gemini, etc.)
npx skills add casvian/the-founders-playbook

Technical Analysis

The first-use setup guide instructs users to execute two npm CLI packages through npx without fixed versions or integrity verification. Package resolution can therefore select code published after this Skill was audited.

Because npx can both retrieve and execute packages, compromise of a referenced package or its distribution channel can turn an apparently legitimate installation command into an arbitrary code-execution path. No evidence in the audited project establishes that either package is presently malicious; the finding concerns the unsafe, mutable dependency-resolution model used by the instructions.

Attack Path

  1. An attacker gains the ability to publish or substitute a malicious release of one of the referenced CLI packages.
  2. The attacker adds harmful CLI entry-point or installation behavior to that release.
  3. A user follows the command in setup.md without independently pinning or inspecting the package.
  4. npx retrieves the attacker-controlled version selected by registry resolution.
  5. The package executes in the user's local environment.
  6. The malicious process performs actions permitted to the invoking account, potentially including reading accessible data, modifying agent or project files, or retrieving further payloads.

Impact Assessment

Exploitation could provide arbitrary local code execution with the invoking user's privileges. Potential exposure includes files writable or readable by that user, process environment variables, local development configuration, and credentials made available to npm or the shell environmen ...[truncated 236 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin both npm CLI packages to reviewed versions in every setup example.
  2. Ensure the versions in setup.md and README.md remain identical to prevent users from following inconsistent installation paths.
  3. Provide package provenance information, including the expected registry, publisher, source repository, and release verification process.
  4. Use package signatures or published artifact hashes when supported.
  5. Consider supplying a lockfile-controlled installation method that separates dependency retrieval from execution and permits inspection before use.
  6. Advise users not to run installation commands with elevated privileges.
  7. Add a maintenance procedure requiring security review before changing pinned dependency versions.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (11)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · AGENTS.md (reported line 25)May include surrounding context.

md
## Key Files

- **`skills/the-founders-playbook/SKILL.md`** — The core skill. Read this first. Contains the full 4-stage AI-native startup framework.
- **`skills/the-founders-playbook/setup.md`** — First-use integration guidance for the skill.

## Stage Detection

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file says the skill 'auto-detects' startup stage based on trigger phrases, yet it does not enumerate those phrases or define when activation should or should not occur. That ambiguity can cause unintended invocation because common startup-related discussion may match without clear scope constraints.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The README instructs users to execute npx clawhub install the-founders-playbook without pinning a specific package version. This creates a supply-chain risk because a future compromised or malicious package release could be fetched and executed automatically on the user's machine. The skill context does not mitigate this risk, since installation commands in documentation are commonly copied and run verbatim.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The README also recommends npx skills add casvian/the-founders-playbook without version pinning or integrity constraints. Because npx resolves and executes packages dynamically, users may unknowingly run changed code if the upstream package, dependency chain, or registry account is compromised. In this context, the risk is real because the command is presented as a normal installation path for any agent user.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill says users can 'start talking naturally' and that 'The agent detects which stage you're in and activates the appropriate playbook,' which is an overly broad activation model. Broad natural-language triggering increases the chance of unintended invocation, prompt collision, or activation during unrelated conversations, potentially causing the agent to apply business-stage guidance in the wrong context or expose internal workflow behavior unexpectedly. Because this skill is designed for any AI agent and any platform, the ambiguity is more dangerous than in a tightly sandboxed environment.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill uses broad natural-language trigger phrases such as 'launch', 'scale', and 'write the code' to activate stages. In a multi-skill or autonomous agent environment, these generic phrases can cause unintended skill activation or stage misclassification, leading the agent to apply the wrong workflow or recommendations without explicit user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill states that stage transitions are detected 'from context' and only asks for clarification when uncertain, but does not define clear decision rules or precedence. This ambiguity can produce nondeterministic behavior, accidental stage transitions, and inappropriate advice, especially when user prompts contain overlapping startup terms or discuss multiple stages at once.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The stage detection table uses very common words like "think," "build," "customers," and "hire" as activation cues without narrowing context or providing exclusions. In a reference intended to guide activation, these broad phrases could overlap with ordinary conversation and trigger the wrong stage selection.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The installation command invokes npx clawhub without pinning a specific package version, so users may execute whatever version is currently published at install time. If the upstream package is compromised, typo-squatted, or updated with malicious behavior, this can lead to arbitrary code execution on the user's machine during installation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The command npx skills add casvian/the-founders-playbook relies on an unpinned package/tool resolution path, which means the code fetched and executed can change over time without review. This creates a supply-chain risk: a compromised publisher, malicious update, or package-resolution abuse could cause users to run attacker-controlled code.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises broad natural-language activation triggers such as 'I have an idea' or 'We need to scale,' which are common phrases in ordinary conversation. In agent environments with automatic skill activation, this can cause unintended triggering, injecting startup-playbook behavior into unrelated contexts and increasing the chance of prompt-scope confusion or unsafe cross-task influence.

Content

No source excerpt is available for this finding.