The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run npx @useclawlink/cli commands to log in, connect services, and execute data retrieval actions.
[EXTERNAL_DOWNLOADS]: The use of npx triggers the download of the @useclawlink/cli package from the NPM registry at runtime.
[DATA_EXPOSURE_AND_EXFILTRATION]: The CLI manages authentication tokens stored in ~/.clawlink/credentials.json and performs network operations to claw-link.dev to proxy requests to Ahrefs.
[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content retrieved from Ahrefs, such as keyword overviews and backlink metadata.
Ingestion points: Data enters the agent's context through the output of CLI actions described in SKILL.md.
Boundary markers: The instructions do not define delimiters or provide warnings to the agent to ignore instructions embedded in the SEO data.
Capability inventory: The skill has access to shell execution via the CLI and network communication through the vendor's proxy.
Sanitization: There is no evidence of filtering or sanitization of the external data before it is processed by the agent.

ahrefs