The Agent Skills Directory

[COMMAND_EXECUTION]: The skill leverages the specify CLI to perform read-only inspection of artifacts, templates, and hooks. While the instructions claim the commands are read-only, it involves executing shell commands in the project environment.
[INDIRECT_PROMPT_INJECTION]: The skill processes and displays output from external CLI commands, which constitutes an ingestion point for untrusted data that could influence the agent's behavior.
Ingestion points: Data returned from specify artifact list, specify artifact info, and specify artifact lookup commands as described in SKILL.md.
Boundary markers: None identified; the agent is not instructed to ignore potential instructions embedded in the artifact data.
Capability inventory: Command execution via the specify CLI tool.
Sanitization: No sanitization or validation of the CLI output is implemented.

speckit-artifact