The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli package from the NPM registry. This package is managed by the vendor associated with the skill.
[COMMAND_EXECUTION]: The skill's primary interface is shell command execution via npx, which allows the agent to interact with the local environment to manage authentication and trigger remote actions.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Neon projects, which could contain malicious instructions designed to influence the agent's behavior when the data is read.
Ingestion points: Data returned by neon_access_project_details_by_id, neon_fetch_database_for_branch, and other retrieval actions in SKILL.md.
Boundary markers: Absent; the instructions do not specify delimiters or warnings for the agent to ignore embedded instructions in the database metadata.
Capability inventory: The agent has the capability to execute shell commands (npx) and read/write to the filesystem based on the CLI's requirements (e.g., storing credentials in ~/.clawlink/credentials.json).
Sanitization: Not explicitly mentioned in the skill instructions.
[DYNAMIC_EXECUTION]: The use of npx involves runtime execution of code fetched from a remote registry, which is a form of dynamic code loading.

neon