The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local openspec CLI commands (openspec list and openspec status) to synchronize with the current project state and retrieve artifact metadata. These commands are intrinsic to the skill's primary purpose of architectural exploration and documentation management.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from the local codebase and CLI outputs. 1. Ingestion points: Data enters the agent context through the output of openspec list --json, openspec status, and the contents of files discovered at existingOutputPaths. 2. Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings for the data read from the codebase. 3. Capability inventory: The agent possesses capabilities to execute shell commands via the openspec CLI and read project files. 4. Sanitization: There is no evidence of validation or sanitization of content retrieved from the filesystem or CLI before it is interpolated into the conversational context.

openspec-explore