ClawHub
Back to skill

Security audit

Blogwatcher Local

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for using a blog/RSS watcher CLI, with the main caveat that it installs that CLI from an unpinned Go module version.

Install only if you trust the blogwatcher upstream project. Prefer a pinned Go module version if available, and review the CLI before using it in environments with sensitive local files or credentials.

A.I.G

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:6
Finding

Unpinned Third-Party Go Dependency

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 6–12
Vulnerability Type: Unpinned executable dependency
Risk Level: Medium

Vulnerable Code

yaml
metadata: {"clawdbot":{"emoji":"📰","requires":{"bins":["blogwatcher"]},"install":[{"id":"go","kind":"go","module":"github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest","bins":["blogwatcher"],"label":"Install blogwatcher (go)"}]}}
sh
go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest

Technical Analysis

The installation metadata and documentation instruct users to install the third-party blogwatcher executable using the mutable @latest version selector. This causes Go to resolve and compile whichever upstream release is considered current at installation time, rather than a version that was reviewed alongside this skill.

The dependency's source code is not included in the audited project, which contains only SKILL.md and _meta.json. Consequently, the effective executable payload can change after this skill has been reviewed. If the upstream repository, maintainer account, module publication process, or a future release is compromised, the installation command could retrieve and build attacker-controlled code.

Attack Path

  1. An attacker compromises the upstream repository, a maintainer account, or its release process.
  2. The attacker publishes a malicious version that becomes the version resolved by @latest.
  3. A user follows the skill's installation instructions or invokes its installation metadata.
  4. Go downloads and compiles the compromised module.
  5. The resulting blogwatcher binary executes attacker-controlled behavior when the user runs it.

Exploitation depends on compromise or malicious modification of the external dependency; no evidence that the currently referenced upstream project is malicious was present in the audited artifact.

Impact Assessment

A compromised dependency could ex ...[truncated 491 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace @latest in both the installation metadata and documentation with a specific reviewed release, for example:
    sh
    go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@vX.Y.Z
  2. Review the source code of the selected release before publishing the updated skill.
  3. Record and verify the expected module checksum through Go's module checksum mechanisms and retain a reviewed dependency manifest where practical.
  4. Prefer cryptographically signed releases or verifiable build provenance when the upstream project provides them.
  5. Introduce dependency update automation that opens explicit version-change reviews rather than silently resolving the newest release.
  6. Re-audit the dependency before changing the pinned version.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

Static analysis

No suspicious patterns detected.