The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data which could potentially contain malicious instructions.
Ingestion points: The skill reads user requests (Step 1), command output from openspec instructions and openspec context, and the content of existing artifact files from the local disk (Step 5a).
Capability inventory: The skill uses the Bash(openspec:*) tool to manage changes and write markdown files (artifacts) to the file system.
Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions when processing external file content or user input.
Sanitization: No sanitization or validation of the ingested content is specified before it is used to influence the generation of new artifacts.
[COMMAND_EXECUTION]: The skill makes extensive use of the openspec CLI to manage the state of the project and retrieve instructions. The execution is scoped to the openspec:* namespace as defined in the allowed-tools frontmatter.

openspec-propose