The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the boha CLI tool through cargo install boha (via crates.io) and paru -S boha (via the Arch User Repository). These are the vendor's own installation paths for the tool described.
[COMMAND_EXECUTION]: The skill documentation includes numerous bash command templates for the boha binary, enabling the agent to execute local searches, data exports, and verification tasks related to cryptographic puzzles.
[PROMPT_INJECTION]: There is a potential for indirect prompt injection as the skill retrieves and processes data from external crypto puzzle databases.
Ingestion points: Data from puzzle collections is ingested via commands like boha list, boha search, and boha show defined in SKILL.md.
Boundary markers: No explicit boundary markers or instructions are provided to the agent to treat content from the puzzle descriptions as untrusted or to ignore embedded instructions.
Capability inventory: The skill enables the agent to open asset URLs in a browser using the --open flag and to pipe tool output into other shell utilities like jq (documented in SKILL.md).
Sanitization: There is no evidence of sanitization or filtering of the text content retrieved from the puzzle collections before it is presented to the agent.

boha-cli