Back to skill

Security audit

Summarize Jarvis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward summarization CLI helper with normal external-provider and package-install risks, but no hidden or destructive behavior in the artifact.

Install only if you are comfortable using the third-party summarize CLI and sending selected content to configured model or extraction providers. Avoid summarizing sensitive, regulated, or confidential files and URLs unless those external disclosures are approved, and review the Homebrew tap/source before installing in a high-trust environment.

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
SKILL.md:5
Finding

Unpinned Third-Party Homebrew Dependency

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 5
Vulnerability Type: Supply-chain risk from a mutable third-party 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 delegates installation of the required summarize executable to the third-party Homebrew tap steipete/tap/summarize. The dependency declaration does not pin an immutable release, commit, or artifact digest, and it does not specify an independent integrity-verification mechanism.

Consequently, the code ultimately installed may change after this skill package has been reviewed. If the tap, its maintainers, the referenced release infrastructure, or another relevant supply-chain component is compromised, an attacker could substitute malicious installation logic or binaries. This is a supply-chain weakness rather than evidence that the currently referenced package is malicious.

Attack Path

  1. An attacker compromises the third-party Homebrew tap, a maintainer account, or an upstream artifact source used by the formula.
  2. The attacker modifies the mutable formula or referenced artifact to distribute malicious code.
  3. A user installs the skill dependency through the declared Homebrew installation method.
  4. Homebrew resolves the altered formula or artifact without a project-defined immutable version or integrity constraint.
  5. The malicious installation logic or executable runs with the privileges of the installing user.
  6. The payload may access data and credentials available to that user, including files supplied for summarization and API keys present in the process environment.

Impact Assessment

Successful exploitation could provide code execution with the installing user's ...[truncated 520 chars]

Remediation
View remediation

Remediation Suggestions

  1. Pin the dependency to an immutable, reviewed release or commit rather than relying only on the mutable tap and formula name.
  2. Verify downloaded artifacts using a cryptographic digest, such as SHA-256, whose expected value is maintained in a trusted project-controlled location.
  3. Prefer an official and auditable distribution channel with signed releases and documented provenance.
  4. Record the exact resolved dependency version and source so installations are reproducible.
  5. Validate signatures and checksums before executing installation scripts or binaries, and fail closed when verification fails.
  6. Review dependency updates before changing the pinned version, including changes to Homebrew formula installation logic and upstream artifact locations.
  7. Perform installation and execution with least privilege, avoiding elevated accounts and limiting access to unrelated files and credentials.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises summarizing URLs, local files, and YouTube content but does not clearly warn users that the referenced content may be transmitted to third-party model providers and optional fallback services such as Firecrawl or Apify. This creates a real privacy and data-handling risk because users may provide sensitive local documents or confidential URLs without understanding they could leave the local environment.

Content

No source excerpt is available for this finding.