The Agent Skills Directory

[SAFE]: The skill performs expected development operations such as searching for files and installing project dependencies using standard tools like npm and ripgrep.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @biomejs/biome package from the official NPM registry and provides links to official Biome release notes on GitHub. These actions are transparent and consistent with the skill's primary function.
[COMMAND_EXECUTION]: Shell commands are used for installation (npm install), initialization (npx @biomejs/biome init), and linting/formatting (npx @biomejs/biome check). These commands are standard for the tool and do not involve unauthorized privilege escalation or persistence mechanisms.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external project files.
Ingestion points: Reads package.json, biome.json, biome.jsonc, and various source code files (JS, TS, CSS, JSON, GraphQL, HTML) as specified in SKILL.md.
Boundary markers: The instructions do not define specific boundary markers or delimiters for the ingested content.
Capability inventory: The skill can execute shell commands (npm, npx, rg) and perform file-write operations (biome check --write) as described in SKILL.md.
Sanitization: There are no explicit sanitization or filtering steps described in the skill for the processed data.

biome