The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the external Buda community forum, which may contain instructions designed to manipulate the agent's behavior.
Ingestion points: Forum posts, replies, and reports are retrieved via the /api/v1/community/ endpoints in scripts/community.mjs.
Boundary markers: No specific delimiters or instructions are present to separate untrusted forum content from the agent's system prompt.
Capability inventory: The agent possesses Bash execution privileges to run the skill CLI, which can perform network requests and access local files.
Sanitization: The raw markdown content of posts and replies is returned without filtering or escaping.
[COMMAND_EXECUTION]: The skill relies on executing a local Node.js script (scripts/community.mjs) for its core functionality, which is an expected behavior using standard libraries.
[EXTERNAL_DOWNLOADS]: The skill interacts with the official Buda community API at buda.im and community.buda.im, which are legitimate service endpoints for this application.

buda-community