Building and packaging applications with Flox. Use for manifest builds, Nix expression builds, sandbox modes, multi-stage builds, and packaging assets.
84
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
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.
Third-party content exposure detected (high risk: 0.70). The skill's required build workflows explicitly run commands that fetch and ingest public third‑party content (e.g., "npm ci" in the Node.js example, the Nix example using fetchurl/mirror://gnu, and the curl icanhazip.com snippet in the Nix shell example) so external, untrusted packages/pages can be pulled into and materially influence build behavior.
32d3e1e
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.