The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to manage the file system and interact with external CLI tools.
Evidence: mkdir -p openspec/changes/archive (SKILL.md)
Evidence: mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name> (SKILL.md)
Evidence: openspec status --change "<name>" --json (SKILL.md)
[PROMPT_INJECTION]: The skill ingests data from local project files and tool outputs to determine execution logic, creating a surface for indirect prompt injection.
Ingestion points: Reads tasks.md to check task completion and parses JSON output from openspec status (SKILL.md).
Boundary markers: Absent. The skill does not specify delimiters or instructions to ignore embedded commands within the files it reads.
Capability inventory: Shell command execution (mkdir, mv), file system read/write access, and the ability to invoke sub-agents via the Task tool (SKILL.md).
Sanitization: Absent. There is no evidence of input validation or escaping for the content of tasks.md or the <name> variable used in shell commands.
[EXTERNAL_DOWNLOADS]: The skill requires a specific command-line interface to be available in the environment.
Requirement: Relies on the openspec CLI for listing, status checks, and synchronization operations.

openspec-archive-change