The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes openspec list --json to retrieve a list of active changes. This is a local operation using the required openspec CLI tool as part of the skill's primary functionality.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading content from artifacts within the openspec/changes/ directory. Ingestion points: Reads files at openspec/changes/<name>/*.md including proposal and task lists. Boundary markers: None explicitly defined in the file reading steps. Capability inventory: Limited to file reading and executing local openspec status commands. Sanitization: The skill includes strict guardrails such as 'Report only' and 'NEVER implement, apply, archive, or modify' to prevent the agent from acting on instructions embedded in the artifacts.

openspec-status