The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the 'openspec' command-line utility to list active changes and gather context.
Evidence: Execution of openspec list --json within SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files and the codebase, representing a potential surface for indirect instructions.
Ingestion points: Reads markdown artifacts in openspec/changes/ and general source code files as directed in SKILL.md.
Boundary markers: None present; the skill lacks specific delimiters to separate user data from instructions.
Capability inventory: Shell command execution via the openspec CLI and file write access for specific design and specification documents.
Sanitization: No validation or sanitization of input file content is performed.

openspec-explore