The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the cli-inbox-reader package globally via npm to enable its core functionality.
[COMMAND_EXECUTION]: The skill extensively uses the inbox-cli command to perform file system operations, network synchronization, and configuration management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from user notes.
Ingestion points: Data is pulled into the agent's context through inbox-cli read, inbox-cli list, and inbox-cli search commands described in SKILL.md.
Boundary markers: Absent. The skill does not define specific delimiters or instructions to treat note content as untrusted data.
Capability inventory: The skill allows for significant system-impacting actions including note creation, modification, deletion, and cloud storage configuration via shell commands in SKILL.md.
Sanitization: Absent. There is no evidence of filtering or validation of the content retrieved from notes before it is processed by the agent.

inbox-reader