The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the openspec CLI tool for querying project state via openspec list and openspec status commands. It also manages the local file system using mkdir and mv commands to move change directories into an archive folder. These operations are consistent with the skill's stated purpose.
[PROMPT_INJECTION]: An indirect prompt injection surface exists because the agent reads and interprets the content of local specification files (specs/*.md) and task lists to resolve conflicts. However, the risk is limited to local project files. 1. Ingestion points: Data is ingested from openspec/changes/<name>/tasks.md and the specs/ directory within each change folder. 2. Boundary markers: No explicit boundary markers or 'ignore' instructions are used when interpreting file content. 3. Capability inventory: The skill can create directories, move files, and execute the openspec CLI. 4. Sanitization: No content sanitization or validation is applied to the interpreted text.

openspec-bulk-archive-change