The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the openspec command-line interface to retrieve status, list changes, and manage stores.
Tools used: openspec list, openspec status, openspec store list.
Scope: Access is restricted to the openspec namespace via the allowed-tools frontmatter configuration.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external Markdown files.
Ingestion points: The agent reads "delta spec" files from the specs/ directory as identified by the openspec status command (SKILL.md, Step 4).
Boundary markers: Absent. The instructions do not include delimiters or warnings to ignore instructions potentially embedded within the specification content.
Capability inventory: The agent possesses file system read/write access and the ability to execute openspec CLI commands.
Sanitization: No escaping, validation, or filtering is applied to the content of the specification files before the agent processes them.

openspec-sync-specs