The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it automatically ingests and processes untrusted data from the user's project environment during its discovery phase.
Ingestion points: The skill reads package.json, lock files, HTML templates, and project source files to detect integration methods and import patterns (Step 2).
Boundary markers: No specific boundary markers or instructions to ignore embedded prompts in project files are defined.
Capability inventory: The skill has the capability to write new files (.font-awesome.md), modify existing source files by inserting generated code and imports (Step 5), and execute shell commands (fa CLI and local Python scripts).
Sanitization: No sanitization or validation of the content read from project files is mentioned before it is used to influence code generation and file modification logic.
[COMMAND_EXECUTION]: The skill relies on executing system commands and local scripts to perform its core functions.
It executes the fa CLI tool for icon lookups, kit operations, and SVG retrieval.
It executes local Python scripts, including scripts/fetch-kit.py, scripts/icon-exists.py, and scripts/latest-version.py, to interact with Font Awesome services.
[EXTERNAL_DOWNLOADS]: The skill communicates with external servers to fetch kit configurations and icon data.
fetch-kit.py: Downloads configuration data from https://kit.fontawesome.com and queries https://api.fontawesome.com via GraphQL.
SKILL.md: References official Font Awesome documentation and management pages at https://docs.fontawesome.com and https://fontawesome.com.

add-icon