Back to skill

Security audit

skill-ts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward wrapper for a summarization CLI, with expected external AI-provider use and a third-party install dependency that users should understand before using sensitive files.

Install only if you are comfortable trusting the third-party Homebrew tap and the configured AI/fallback providers. Avoid summarizing confidential local files, private URLs, or proprietary media unless your provider and workplace policies allow that data to be sent to external services.

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## Vulnerability Details **File Location**: `SKILL.md`, line 5 **Vulnerability Type**: Unpinned dependency from a third-party Homebrew tap **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 installation metadata directs users or an automated agent to install the `summarize` executable from the third-party Homebrew tap `steipete/tap`. The dependency is not pinned to an immutable version or source commit, and the configuration provides no checksum or signature for integrity verification. Consequently, the executable installed in the future may differ from the component that existed when this Skill was reviewed. This creates a supply-chain trust boundary: compromise of the tap, its maintainer account, its referenced release artifacts, or its distribution infrastructure could cause installation of attacker-controlled code. No evidence indicates that the current dependency is malicious. The issue is the absence of controls ensuring that future installations retrieve the reviewed artifact. ### Attack Path 1. An attacker compromises the third-party Homebrew tap, a maintainer account, or an upstream artifact referenced by its formula. 2. The attacker modifies the formula or release artifact to contain malicious installation logic or a malicious `summarize` executable. 3. A user or agent follows the Skill metadata and installs `steipete/tap/summarize`. 4. Homebrew retrieves and processes the modified formula or artifact because no immutable version, commit, checksum, or signature is enforced by this project. 5. Malicious code executes during installation or when the installed `summarize` command is subsequently invoked. ### Impact Assessment Successful exploitation could execute arbitr ...[truncated 512 chars]
Remediation
## Remediation Suggestions - Prefer an official, reviewed distribution channel rather than an unverified third-party tap. - Pin the dependency to an immutable release version or source commit instead of tracking a mutable formula. - Verify downloaded artifacts using a cryptographic checksum supplied through a trusted channel. - Where supported, verify a cryptographic release signature and document the expected signing identity. - Record the exact upstream repository and reviewed artifact so maintainers can reproduce and validate the installation. - Execute installation and the resulting CLI with the least privileges necessary; do not install or run it as an administrator unless strictly required. - Add routine dependency monitoring and re-audit the pinned artifact before approving version updates.
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
Confidence
96% confidence
Finding
The skill explicitly instructs users to provide URLs, local files, PDFs, images, audio, and YouTube links to a third-party summarization CLI, and it lists multiple external AI providers and optional fallback services. However, it does not warn that submitted content may be transmitted off-host to those providers, which can expose sensitive local files, internal URLs, or proprietary content without informed user consent.

Static analysis

No suspicious patterns detected.