pleaseai/bun
All-in-one JavaScript/TypeScript toolkit: fast runtime, package manager, test runner, and bundler. Version-aware skill backed by the ask CLI.
75
94%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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 skill’s runtime workflow uses `ask src "github:oven-sh/bun@${BUN_REF}"` / `ask docs ...` to fetch Bun source/docs from GitHub (public web content) and injects that readable text into the agent context, which is outsider-authored free text.
Where we found it
github:oven-sh/bun
domain · 17 sites
The plugin uses `ask src` and `ask docs` to fetch Bun source code and documentation from the GitHub repository `github:oven-sh/bun` at runtime, injecting that outsider-authored content into the agent context for API verification and code generation.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill includes a runtime installation command that fetches and executes remote code via curl -fsSL https://bun.sh/install | bash, and it also relies on runtime fetches of the repository via ask (github:oven-sh/bun@${BUN_REF}) to drive API verification and generated code, so external content is fetched/executed and directly influences the agent's behavior.
Where we found it
curl -fsSL https://bun.sh/install | bash
command · 1 site
The plugin instructs the agent to install Bun by piping a remote install script from https://bun.sh/install directly to bash, which fetches and executes unverified remote code at runtime.
SKILL.md:27
github:oven-sh/bun
dependency · 17 sites
The plugin fetches Bun source code and documentation from the GitHub repository `github:oven-sh/bun` at runtime via `ask src` and `ask docs`, and this fetched external content directly drives API verification and generated code — an unverifiable external dependency that influences agent behavior.
- Audited
- Security analysis