The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to interact with the openspec CLI (openspec list, openspec status) and performs file system operations including directory creation (mkdir -p) and moving project files (mv) to an archive location.
[INDIRECT_PROMPT_INJECTION]: The skill reads and interprets requirements from local markdown files to make logic decisions, creating a potential vector for malicious data to influence the agent.
Ingestion points: Reads completion status from openspec/changes/<name>/tasks.md and parses requirement names from delta spec files in openspec/changes/<name>/specs/.
Boundary markers: The instructions do not specify any delimiters or safety prompts to ensure the agent ignores hidden instructions within the processed markdown files.
Capability inventory: The skill has the capability to execute shell commands and perform codebase searches, which could be abused if the agent follows instructions embedded in the specs.
Sanitization: No validation or escaping is performed on the content of the tasks.md or spec files before they are processed by the agent's logic.

openspec-bulk-archive-change