The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a specific local command to perform its primary function.
Evidence: The skill body contains the instruction: Run quest skill export and follow its output.
[EXTERNAL_DOWNLOADS]: The skill directs the user or agent to an external, unverified GitHub repository for setup and installation instructions.
Evidence: Found in SKILL.md: https://github.com/kixelated/quest/blob/main/SETUP.md
[INDIRECT_PROMPT_INJECTION]: The skill ingests quest data from an external source (the quest tool) and processes it to create GitHub issues, which presents a surface for indirect prompt injection if the source data is attacker-controlled.
Ingestion points: Data retrieved from the quest CLI tool (SKILL.md).
Boundary markers: None specified in the instructions to separate data from instructions.
Capability inventory: Command execution via quest skill export (SKILL.md).
Sanitization: No sanitization or validation steps are mentioned for the quest data before it is processed.

quest-export