The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the SocialClaw CLI tool from the public npm registry at a pinned version (socialclaw@0.1.12).
[EXTERNAL_DOWNLOADS]: The skill suggests an optional installation of a third-party plugin @xquik/tweetclaw@1.6.31 for enhanced X/Twitter operations.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for credential validation (curl), package installation (npm), and social media management (socialclaw).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and display data from external social media platforms (e.g., status updates, delivery analytics, search results from TweetClaw), creating an attack surface where malicious content from those platforms could influence agent behavior.
Ingestion points: Data enters the agent's context through socialclaw status, socialclaw posts list, and output from the tweetclaw plugin (e.g., search results, mentions).
Boundary markers: No specific boundary markers or 'ignore' instructions are defined to separate external data from system prompts.
Capability inventory: The skill possesses the capability to execute shell commands, perform network requests via CLI, and read/write local files (e.g., schedule.json, media assets).
Sanitization: There is no evidence of sanitization, escaping, or validation of content retrieved from social media providers before it is presented to the agent.

social-publisher