Summarize Cli

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 3:40 AM UTC
• Version: 1.0.0

Overview

This skill is a straightforward wrapper for a summarization CLI, but users should understand the external tool and data-handling implications before using it on sensitive files or URLs.

Install only if you trust the `summarize` CLI and its Homebrew tap. Avoid using it on confidential documents, private media, or sensitive URLs until you understand whether the CLI sends content or metadata to external services, and remember that `--output` saves summaries to local disk.

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 Executable Dependency from a Third-Party Homebrew Tap

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, line 5
Vulnerability Type: Supply-chain risk from an unpinned third-party executable dependency
Risk Level: Medium

Vulnerable Code Snippet:

yaml

metadata: {"clawdbot":{"emoji":"🧾","requires":{"bins":["summarize"]},"install":[{"id":"brew","kind":"brew","formula":"steipete/tap/summarize","bins":["summarize"],"label":"Install summarize (brew)"}]}}

Technical Analysis

The skill declares installation of the summarize executable from the third-party Homebrew tap steipete/tap. The dependency is not constrained to a specific version, source commit, or cryptographic checksum. Consequently, the executable and its installation behavior may change after this skill has been reviewed without requiring any modification to the audited project.

Homebrew formula installation can download and execute external build or installation logic. If the tap, formula repository, upstream release infrastructure, or maintainer account is compromised, the dependency could be replaced with malicious code. The resulting binary would later be invoked on URLs and local files according to the documented skill behavior.

The audit found no evidence that the current external package is malicious. The vulnerability is the absence of dependency pinning and integrity verification, which prevents the reviewed project from guaranteeing that future installations resolve to the same audited artifact.

Attack Path

1. An attacker compromises the third-party Homebrew tap, its maintainer account, or the upstream artifact distribution channel.
2. The attacker modifies the formula or referenced artifact to install a malicious summarize executable.
3. A user or agent follows the skill metadata and installs steipete/tap/summarize.
4. Homebrew retrieves and installs the attacker-controlled package without a project-level version or integrity constraint.
5. The agent invokes summarize o ...[truncated 937 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin the dependency to a specific, reviewed release rather than resolving the latest formula dynamically.
2. Record and verify a cryptographic checksum for the downloaded artifact.
3. Where practical, pin the tap or source repository to an immutable commit and document the corresponding upstream source.
4. Prefer a trusted package source with reproducible builds, signed releases, and transparent provenance.
5. Verify package signatures or checksums before installation and fail closed if verification does not succeed.
6. Run the CLI with least privilege and restrict its access to unrelated local files, credentials, environment variables, and network destinations.
7. Periodically review the pinned dependency and its transitive dependencies before upgrading.

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

Low

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The skill encourages summarizing URLs, PDFs, images, audio, and YouTube content via an external CLI without warning that user-supplied content may be transmitted to external services or processed outside the local environment. It also documents --output <file> without noting that summaries are written to disk, which can create unintended data retention or leakage risks when users handle sensitive material.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.