T08 · Insecure Dependencies
- Location
SKILL.md:166- Finding
Unverified Installation of Third-Party Skills
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 166, 201, 276, 297, and 318
Vulnerability Type: Third-party supply-chain exposure through unverified installation guidance
Risk Level: MediumVulnerable Code Snippets
text clawhub install email-auto-sortertext clawhub install code-assistant-protext clawhub install ppt-generator-aiTechnical Analysis
The Skill instructs users to install third-party Skills directly by package name. It does not require validation of the package publisher, source repository, package version, cryptographic signature, checksum, requested permissions, or independent security review before installation.
Although the document describes rating, download-count, and update-frequency criteria, the audited project contains no implementation that retrieves or verifies this metadata. Consequently, the example ratings and popularity claims cannot be treated as security controls or evidence that the named packages are authentic.
Name-only installation creates supply-chain risk because package ownership and package contents can change independently of this reviewed document. It may also expose users to typosquatting, name takeover, publisher impersonation, or a malicious package using a recommended name. The audit did not establish that any named package is currently malicious; the vulnerability is the absence of verification before installation.
Attack Path
- An attacker publishes, impersonates, or takes control of a Skill using a recommended or confusingly similar package name.
- A user invokes this advisor and receives the documented name-only installation command.
- The user runs the command without verifying the publisher, source, version, integrity, or requested privileges.
- ClawHub downloads and installs the attacker-controlled package.
- When the installed Skill is loaded or invoked, its instructions or executable components ...[truncated 1004 chars]
- Remediation
View remediation
Remediation Suggestions
- Query current registry metadata before making a recommendation rather than relying on static names, ratings, or download counts.
- Verify the publisher identity, ownership history, official source repository, maintenance status, and security-review status of every recommended Skill.
- Pin installation recommendations to a reviewed version and verify a trusted cryptographic signature or checksum where supported.
- Display the permissions, tools, filesystem paths, credentials, and network destinations requested by the Skill before installation.
- Clearly mark fictional or illustrative package names, ratings, and download counts as examples that must not be treated as verified registry data.
- Require explicit user confirmation after presenting provenance and permission information.
- Recommend initial execution in an isolated, low-privilege sandbox without production credentials or sensitive data.
- Prefer an allowlist of reviewed publishers and packages, and reject ambiguous, unowned, unsigned, or unexpectedly changed packages.
- Revalidate package integrity and publisher ownership on updates instead of implicitly trusting later releases.
