The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use shell commands such as curl for API interactions, chmod for securing credential files, and npx for package management.
[EXTERNAL_DOWNLOADS]: Suggests the installation of related skills using the npx command targeting the vendor's repository.
[INDIRECT_PROMPT_INJECTION]: The skill has an indirect injection surface as it directs the agent to fetch and process runtime instructions from an external URL (https://www.pixazo.ai/models/firered-image-edit.md).
Ingestion points: Remote documentation URL defined in the 'Full reference' section of SKILL.md.
Boundary markers: None identified for the remote content.
Capability inventory: Subprocess execution via curl and npx, local file system writes, and network operations through Python requests and Node.js fetch.
Sanitization: No explicit sanitization or validation logic is defined for the content fetched from the remote reference.
[DATA_EXPOSURE]: The skill manages a sensitive API key stored in ~/.pixazo/api-key. It adheres to security best practices by recommending restrictive file permissions (chmod 600) to prevent unauthorized local access.

firered-image-edit