Bigdeal Supplier Finder

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 9:33 AM UTC
• Version: 1.0.0

Overview

This skill is a bounded supplier-research guide that uses public web search and fetch, with the main caution being unpinned upgrade instructions.

Install only if you are comfortable with a skill that performs public supplier web research and produces evidence-bound reports. Do not authorize browser sessions, credentials, paid APIs, form submissions, or bulk crawling for this skill unless you separately review that boundary. For updates, prefer inspecting or pinning the repository/installer revision instead of blindly running the unpinned latest command.

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:290

Finding

Unpinned Third-Party Package and Repository Execution in Upgrade Instructions

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, line 290
Vulnerability Type: Unpinned third-party dependency and mutable upstream source
Risk Level: Medium

Vulnerable Code

markdown

## Source & Upgrade

- **Repository**: https://github.com/its-How/bigdeal-supplier-finder
- **Upgrade**: Run `git pull` in the skill directory, or re-run `npx skills add its-how/bigdeal-supplier-finder` to get the latest version.
- **Uninstall**: Delete the `bigdeal-supplier-finder/` directory from your skills path.

Technical Analysis

The documented upgrade command invokes npx with the unversioned package name skills and instructs it to install a Skill from an unpinned GitHub repository reference. Neither the command-line package version nor an immutable repository commit is specified.

Because these sources are mutable, code retrieved during a future upgrade may differ from the content covered by this audit. If the npm package, its publisher account, the GitHub repository, or a related distribution channel is compromised, following the documented command could retrieve and execute attacker-controlled package logic. The alternative git pull instruction likewise imports the current upstream branch rather than a reviewed commit, although it does not by itself establish that newly retrieved code is executed automatically.

No evidence indicates that the currently reviewed project contains a malicious payload. The vulnerability is the unsafe supply-chain update mechanism and the trust placed in mutable third-party sources.

Attack Path

1. An attacker compromises the npm package, publisher account, upstream repository, or another relevant distribution mechanism.
2. The attacker publishes a malicious package release or malicious Skill revision.
3. A user follows the documented upgrade command: npx skills add its-how/bigdeal-supplier-finder
4. npx resolves the unpinned CLI package, and the CLI re ...[truncated 904 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin the skills CLI to a reviewed exact version, for example by using an explicit package version rather than an unversioned npx invocation.
2. Pin the Skill source to an immutable Git commit or cryptographically signed release tag instead of the repository's current default branch.
3. Publish and verify SHA-256 checksums or signed provenance for downloaded artifacts before installation.
4. Separate retrieval from execution so users can inspect the resolved package and Skill contents before running installation logic.
5. Use a lockfile or equivalent dependency manifest to preserve reviewed transitive dependency versions.
6. Run upgrades in a sandbox with minimal filesystem, environment-variable, credential, and network access.
7. Replace the generic git pull recommendation with a documented process that fetches, verifies, reviews, and then checks out a specific approved commit.
8. Require a new security review whenever the pinned package version or Skill commit changes.

SkillSpector

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (3)

Credential Access

High

• Category: Privilege Escalation
• Confidence: 70% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md

Do not:

- log in, handle cookies, read sessions, solve captcha, bypass access controls, use paid APIs, or access credentialed sources;
- run recursive crawling, bulk scraping, database storage, contact enrichment, or background monitoring;
- label suppliers as trustworthy, safe, recommended, best, verified, compliant, or purchase-ready;
- count search pages, query-only snippets, AI answers without public URLs, failed fetches, restricted pages, paywalls, login walls, captcha pages, or D-grade raw signals as actionable leads.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The invocation description is extremely broad and covers many common sourcing and supplier-research tasks, making the skill likely to auto-trigger in situations beyond the author's narrow intent. Over-broad matching can route unrelated prompts into a web-search/fetch workflow, increasing the chance of unnecessary external access, data exposure to third-party sites, or unsafe tool use in contexts that needed tighter scoping.

Content

No source excerpt is available for this finding.

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 78% confidence

Finding

The skill instructs users to run npx skills add its-how/bigdeal-supplier-finder without pinning a specific version or integrity mechanism. This creates a supply-chain risk because a future malicious or compromised package release could be executed implicitly at install time, especially since npx may fetch and run code directly.

Content

No source excerpt is available for this finding.