Blogwatcher.Old

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 8:46 AM UTC
• Version: 1.0.0

Overview

This is a straightforward blog/RSS monitoring helper, with the main caution that it installs a mutable third-party Go CLI using @latest.

Install only if you trust the upstream blogwatcher project and are comfortable with a Go module fetched at install time. For better reproducibility, prefer a pinned reviewed version or commit instead of @latest.

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:11

Finding

Unpinned Third-Party Go Module Installation

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 11–20 and 29–31
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

Vulnerable Code

yaml

      "install":
        [
          {
            "id": "go",
            "kind": "go",
            "module": "github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest",
            "bins": ["blogwatcher"],
            "label": "Install blogwatcher (go)",
          },
        ],

markdown

Install

- Go: `go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest`

Technical Analysis

Both the metadata-driven installation configuration and the manual installation instructions direct users to install the mutable @latest version of a third-party Go module. No reviewed release version, immutable commit, expected checksum, or artifact provenance is specified.

Consequently, the effective source code installed by the Skill can change after this Skill has been audited. The installation also resolves and builds upstream dependencies that are not included in the audited project. If the upstream repository, maintainer account, release process, or transitive dependency chain is compromised, a future installation could produce an attacker-controlled executable.

The audited project does not contain the implementation of blogwatcher, so the behavior of the resulting binary cannot be verified from the sole local file.

Attack Path

1. An attacker compromises the upstream repository, a maintainer account, the release pipeline, or a relevant dependency.
2. The attacker publishes malicious source code as the version selected by @latest.
3. A user or agent follows the Skill metadata or documented command and runs:

   sh

   go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest
   

4. Go downloads and compiles the altered upstream source and its dependencies.
5. The user invokes blogwatcher acc ...[truncated 800 chars]

Remediation

View remediation

Remediation Suggestions

1. Replace @latest with a specific reviewed release version, such as an exact semantic version.
2. For stronger immutability, pin the dependency to a reviewed commit and document the corresponding source revision.
3. Verify module checksums through the Go checksum database or an organization-controlled verification process.
4. Record the reviewed version, expected provenance, and update procedure in SKILL.md.
5. Audit the pinned module and its transitive dependencies before approving version updates.
6. Prefer signed releases or artifacts with verifiable build provenance where available.
7. Keep the metadata installation entry and manual installation command synchronized so neither path falls back to @latest.

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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

Static analysis

No suspicious patterns detected.