The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the socialclaw package and the @xquik/tweetclaw plugin from the NPM registry to enable its functionality.
[COMMAND_EXECUTION]: The skill provides numerous shell commands for managing social media accounts, uploading assets, and publishing posts using the socialclaw CLI.
[INDIRECT_PROMPT_INJECTION]: The skill retrieves post status and lists existing posts from social media platforms, which introduces an attack surface where malicious instructions embedded in social media content (like comments or post text) could potentially influence the agent's behavior.
Ingestion points: Data returned by socialclaw status --run-id <run-id> --json and socialclaw posts list --json (SKILL.md).
Boundary markers: The instructions do not provide delimiters or specific warnings to ignore instructions within the retrieved social media content.
Capability inventory: The agent has access to shell command execution (socialclaw), network operations (curl), and package management (npm) (SKILL.md).
Sanitization: There is no evidence of sanitization, filtering, or validation performed on the text content retrieved from social media platforms.

social-publisher