openspec-archive-change
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the openspec CLI for workflow state management (list, status, instructions) and uses standard shell utilities (mkdir, mv) to organize the file system. These operations are scoped to the project's local directory.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and consider context, operationGuidance, and rules returned by the openspec instructions command. \n
- Ingestion points: Data enters the agent context through the JSON output of openspec instructions archive in Step 1 and openspec instructions specs in Step 4. \n
- Boundary markers: The skill includes explicit instructions for the agent to treat external guidance as advisory and separate from built-in steps, user choices, and CLI contracts. \n
- Capability inventory: The agent has the ability to read files, modify the filesystem (mkdir, mv), and invoke the openspec CLI for spec synchronization. \n
- Sanitization: The instructions mandate reporting conflicts between external guidance and controlling inputs, and prohibit copying guidance text verbatim into project artifacts.
Audit Metadata