The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external sources, specifically the output of the openspec CLI and project-related files.
Ingestion points: The skill reads JSON output from openspec instructions and openspec status, and it re-reads dependency artifact files from the disk during the planning process.
Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between trusted instructions and potentially untrusted content within the files it reads.
Capability inventory: The skill is authorized to execute openspec CLI commands and write files to the local file system at paths determined by the CLI output.
Sanitization: There is no evidence of sanitization or validation for the data received from the CLI or external files before it is used to influence the agent's behavior or output.
[COMMAND_EXECUTION]: The skill's primary functionality relies on executing a series of shell commands via the openspec CLI.
Evidence: The skill uses commands such as openspec new change, openspec status --json, and openspec instructions --json to manage the workflow state and retrieve the instructions for creating artifacts.

openspec-propose