The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx @useclawlink/cli to download and run the ClawLink CLI tool from the public NPM registry. This package is a resource provided by the skill's vendor.
[COMMAND_EXECUTION]: The skill performs shell operations using npx to manage the authentication lifecycle and execute OpenAI API actions.
[CREDENTIALS_UNSAFE]: The setup instructions state that authentication credentials for the ClawLink service are stored locally in the user's home directory at ~/.clawlink/credentials.json. This is standard behavior for CLI-based authentication but involves the creation of a sensitive file.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge to OpenAI, processing external data such as chat completions and audio transcriptions which may contain embedded instructions.
Ingestion points: Data is ingested from external OpenAI API responses via the run command in SKILL.md.
Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters or protective wrappers when processing output from OpenAI.
Capability inventory: The skill has the capability to execute shell commands and interact with the network via the CLI.
Sanitization: Absent. There are no instructions for the agent to sanitize or validate the content received from external API calls before processing it further.

openai