The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The documentation references an installation command for the Superthread CLI via a Homebrew tap (steveclarke/tap/superthread). This resource is owned by the skill author and is considered a vendor-controlled asset.
[COMMAND_EXECUTION]: The skill is designed to interact with the system by executing shell commands through the suth CLI tool to perform project management tasks.
[PROMPT_INJECTION]: The skill processes data retrieved from the Superthread API (such as card content and comments), which introduces a potential surface for indirect prompt injection.
Ingestion points: External data is fetched through commands like suth cards get, suth search query, and suth comments get as described in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or guardrails to differentiate between Superthread data and agent instructions.
Capability inventory: The skill executes CLI commands and provides the ability to open resources in a web browser using the --open or -o flags.
Sanitization: There is no evidence of data sanitization or filtering applied to the content retrieved from the external API before it is presented to the agent.

superthread