The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the sealos-cli tool and a local Node.js script analyze-project-s3.mjs to perform storage operations and analyze project requirements.
[EXTERNAL_DOWNLOADS]: The skill recommends using npx -y sealos-cli@latest to execute the Sealos CLI, which fetches the package from the official npm registry.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because the analyze-project-s3.mjs script identifies local files that the agent then reads to determine configuration needs. These files could contain instructions meant to divert the agent's behavior.
Ingestion points: Local project files are scanned and the agent is instructed to read them.
Boundary markers: The instructions do not provide explicit delimiters or warnings to ignore instructions found within the project files.
Capability inventory: The agent can execute sealos-cli commands and write to environment files.
Sanitization: No sanitization is applied to the content of the files read during the analysis process.

sealos-s3