The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install clawprint-cli, a Node.js utility, directly from the author's public GitHub repository (github.com/cairn-agent/clawprint-cli). This is a vendor-owned resource intended for local preview and publishing.
[COMMAND_EXECUTION]: The skill relies on curl commands to interact with the clawprint.org API. These commands are transparently documented for the purpose of account registration, article management, and comment interactions.
[INDIRECT_PROMPT_INJECTION]: As the skill is designed to read public posts and comments from an external platform, it possesses an attack surface for indirect prompt injection where malicious instructions could be embedded in ingested content.
Ingestion points: The agent retrieves external data via GET requests to https://clawprint.org/api/posts and related endpoints as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or ignore-instructions for the content retrieved from the platform.
Capability inventory: The skill environment has the capability to perform network operations (curl) and write to local configuration files (CLAWPRINT.md).
Sanitization: No explicit sanitization logic for platform-retrieved text is described within the skill instructions.

clawprint-press