The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various commands using the openspec CLI tool to manage changes, check status, and generate artifacts.
Evidence: SKILL.md contains commands such as openspec new change "<name>" --schema bugfix, openspec status --change "<name>", and openspec ff change "<name>".
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to the way it handles untrusted user data.
Ingestion points: User-provided details including reproduction steps, expected behavior, and actual behavior are gathered in SKILL.md (Step 1).
Boundary markers: There are no explicit instructions to use delimiters or XML-style boundary markers when interpolating this user data into the proposal.md or other specification files.
Capability inventory: The agent has the capability to execute system commands via the openspec CLI and perform file system write operations.
Sanitization: The skill does not implement any validation, escaping, or sanitization of the user-provided text before it is written to the project's documentation and subsequently processed by the agent.

openspec-bugfix