Skill Seekers Tool

• Outcome: Pass
• Latest audit: Sep 15, 2026 · 12:52 AM UTC
• Version: 1.0.0

Overview

This skill is a straightforward guide for installing and using a document-to-skill conversion CLI, with normal but important privacy and dependency-installation cautions.

Install only from a trusted Python environment, preferably a virtual environment, and avoid broad extras unless needed. Before converting local files, private repositories, or documents, make sure you are authorized to reuse that content and review outputs for secrets or personal data.

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:17

Finding

Unpinned Third-Party Package Installation

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 17-24 and 94-109
Vulnerability Type: Unpinned and unverified third-party dependencies
Risk Level: Medium

Vulnerable Code

bash

pip install skill-seekers

bash

pip install skill-seekers[all-llms,video,docx,epub,chroma]

Additional optional installation commands include:

bash

pip install skill-seekers[mcp]
pip install skill-seekers[video]
pip install skill-seekers[docx]
pip install skill-seekers[chroma,weaviate]

Technical Analysis

The documented installation commands retrieve the latest version of skill-seekers and its selected transitive dependencies from PyPI without version constraints, cryptographic hashes, a lock file, or other integrity verification.

Because package names resolve to mutable external artifacts, the reviewed SKILL.md does not determine what code will ultimately be installed. A future compromised or malicious package release could therefore execute code that was not present during this audit. Selecting broad extras such as all-llms, video, docx, epub, and chroma further increases the number of transitive dependencies and the associated supply-chain attack surface.

The project contains no executable source code with which to verify the behavior of the external package. Although the documented package name corresponds to the stated PyPI and GitHub resources, the absence of pinned versions and hashes prevents reproducible, integrity-checked installation.

Attack Path

1. An attacker compromises the skill-seekers PyPI project, a maintainer account, the release process, or one of its transitive dependencies.
2. The attacker publishes a malicious release under the expected package name or through a dependency selected by an optional extra.
3. A user follows the documentation and runs an unpinned pip install command.
4. Pip resolves and downloads the affected release because ...[truncated 1253 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin skill-seekers to a specifically reviewed version rather than installing the latest available release:

   bash

   pip install "skill-seekers==REVIEWED_VERSION"
   

2. Provide a hash-locked requirements file generated from reviewed artifacts, and require hash verification:

   bash

   pip install --require-hashes -r requirements.txt
   

3. Lock and review transitive dependencies, including each dependency introduced by optional extras.

4. Avoid recommending the broad all-llms installation unless all included features are required. Document minimal, task-specific extras instead.

5. Recommend installation and execution in an isolated virtual environment or container using a non-administrative account.

6. Document how users can verify the package source, expected release version, artifact hashes, and maintainer signatures where available.

7. Periodically audit pinned package versions and dependency lock files for known vulnerabilities, updating pins only after review and testing.

SkillSpector

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The skill encourages fetching and converting content from external websites, GitHub repositories, and local files, but it does not warn users that these inputs may contain sensitive, proprietary, or personal data. In a skill-generation context, this can lead to unintentional ingestion, packaging, or redistribution of confidential material and increases privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The skill instructions and activation conditions are presented in Chinese, which imposes a specific language on users without indicating that other languages are supported or optional. Under the language/locale policy, forcing a language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.