openspec-update-change
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill interacts with the system by executing the openspec CLI to inspect project state and retrieve artifact details. These operations are limited to the tool's defined scope.
- [INDIRECT_PROMPT_INJECTION]: The skill processes CLI output, which is a potential surface for indirect prompt injection. This risk is managed by explicit instructions to confirm all edits with the user and a prohibition on modifying source code.
- Ingestion points: The skill reads JSON data from openspec status, list, and instructions commands.
- Boundary markers: All file modifications require explicit user confirmation after drafting in the conversation.
- Capability inventory: The skill can read and write to documentation files via CLI-directed paths.
- Sanitization: The skill utilizes structured CLI data and human review as primary safeguards.
Audit Metadata