Summarizer (x64 infrastructure)

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 8:22 PM UTC
• Version: 1.0.3

Overview

This skill is a straightforward wrapper for a third-party summarization CLI, with normal privacy and supply-chain cautions for cloud AI summarization.

Install only if you trust the speechybubble summarize package and the providers you configure. Avoid using it on secrets, regulated data, or proprietary files unless sending that content to the selected AI or extraction service is approved.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:5

Finding

Unpinned Third-Party Executable Dependency

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, line 5
Vulnerability Type: Unpinned package-manager dependencies from third-party sources
Risk Level: Medium

Vulnerable Code

yaml

metadata: {"openclaw":{"emoji":"🧾","requires":{"bins":["summarize"]},"install":[{"id":"npm","kind":"node","package":"@speechybubble/summarize","bins":["summarize"],"label":"Install summarize (npm, speechybubble)"},{"id":"brew","kind":"brew","formula":"speechybubble/tap/summarize","bins":["summarize"],"label":"Install summarize (brew, macOS)","os":["darwin"]}]},"clawdbot":{"emoji":"🧾","requires":{"bins":["summarize"]},"install":[{"id":"npm","kind":"node","package":"@speechybubble/summarize","bins":["summarize"],"label":"Install summarize (npm, speechybubble)"},{"id":"brew","kind":"brew","formula":"speechybubble/tap/summarize","bins":["summarize"],"label":"Install summarize (brew, macOS)","os":["darwin"]}]}}

Technical Analysis

The installation metadata identifies @speechybubble/summarize from npm and speechybubble/tap/summarize from a custom Homebrew tap without specifying an immutable package version, source commit, artifact checksum, or integrity digest. Consequently, the implementation installed by a user can differ from the implementation that existed when this Skill was reviewed.

This creates a supply-chain trust boundary: control over the npm publisher account, package release process, source repository, Homebrew tap, or distributed artifacts can alter the executable installed under the trusted summarize name. If a future or compromised release contains malicious installation hooks or runtime behavior, package installation or later invocation could execute that behavior locally.

The project does not itself contain evidence that the referenced package or formula is malicious. The vulnerability is the absence of dependency pinning and artifact-integrity controls, which prevents this Skill package from guaranteeing what executable code will ...[truncated 1640 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin the npm dependency to a specific audited version rather than resolving the latest available release.
2. Record and verify the npm artifact's integrity hash using lockfile or equivalent package-manager integrity metadata.
3. Pin the Homebrew installation to an immutable formula revision or source commit and verify the downloaded artifact with a cryptographic checksum.
4. Prefer installation sources with signed releases, protected publisher accounts, multi-factor authentication, and auditable release provenance.
5. Review whether the npm package defines lifecycle scripts such as preinstall, install, or postinstall; disable unnecessary scripts during installation where operationally possible.
6. Add reproducible-build or provenance verification so maintainers can confirm that distributed binaries correspond to reviewed source code.
7. Establish an update process in which dependency upgrades are reviewed and tested before changing the pinned version or digest.
8. Document the permissions, network access, files, and environment variables required by the executable, and run it with the least privileges necessary.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The skill explicitly supports summarizing URLs and local files and lists multiple third-party model providers, which implies user-supplied content may be transmitted off-host to external services. Because the skill does not warn users that local file contents, extracted web content, and optional fallback service data may be sent to OpenAI, Anthropic, Google, xAI, Firecrawl, or Apify, users could unknowingly expose sensitive or proprietary data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.