The Agent Skills Directory

[COMMAND_EXECUTION]: Employs curl, jq, and the zero CLI tool to interact with the Buffer API. The skill writes temporary JSON configuration files to the /tmp/ directory to manage GraphQL request payloads.
[PROMPT_INJECTION]: Vulnerable to indirect prompt injection as it retrieves and processes content from external social media platforms.
Ingestion points: Fetches organization names, channel IDs, and existing social media post text from the Buffer API endpoint (api.buffer.com).
Boundary markers: The provided templates do not include specific delimiters or instructions for the agent to ignore potentially malicious content within retrieved data.
Capability inventory: Has the ability to create, modify, and delete posts across multiple social media channels using curl and environment-stored credentials.
Sanitization: The skill lacks explicit logic to sanitize or validate external content before it is incorporated into the agent's context or used in subsequent API calls.

buffer