The Agent Skills Directory

[SAFE]: The skill provides documentation for the official Linode command-line interface. All external links point to official Linode, Akamai, or GitHub repositories associated with the vendor. Installation instructions use the standard Python package manager (pip) for the official linode-cli package. The skill also explicitly promotes secure practices, such as rotating API tokens and using environment variables for authentication.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from the Linode API, creating a potential surface for indirect prompt injection if external data (such as resource labels or tags) is maliciously crafted.\n
Ingestion points: Data enters the agent's context through shell command outputs from the linode-cli tool (SKILL.md).\n
Boundary markers: The documentation examples do not include explicit boundary markers or instructions to ignore embedded commands in the CLI output.\n
Capability inventory: The skill uses pip3 for package management and linode-cli, jq, and openssl for infrastructure operations (SKILL.md).\n
Sanitization: Examples include the use of jq -r for structured data extraction and shell variable quoting, which are standard practices for mitigating injection risks in automated scripts.

linode-cli