native-wsl-workspaces
Reliably inspect, create, edit, validate, and transfer files in a Windows-hosted WSL workspace. Use when a task names a WSL path, a `\\wsl.localhost` path, a Windows/WSL project location, or when remote file writes, UNC paths, mounted workspaces, and WSL shell execution may disagree.
75
94%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The workflow downloads files from arbitrary URLs using curl via `install_verified_url.sh`, risking indirect prompt injection if an untrusted URL is processed.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill downloads external code via a runtime-supplied URL in install_verified_url.sh without establishing an official first-party publisher, constituting an unverified external dependency.
- Repository
- pvnkmnk/AgenticSelfHostSkills
- Commit
ff4471e
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.