openspec-develop
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns detected. The skill instructions focus on legitimate development automation and include safety measures such as human-in-the-loop confirmation for architectural decisions and scope expansion checks.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files which could theoretically contain malicious instructions if the codebase is compromised.
- Ingestion points: Reads tasks.md, design.md, and project.md via the Read tool.
- Boundary markers: No explicit delimiters are used to wrap ingested content.
- Capability inventory: The skill can perform Write, Edit, and Bash operations.
- Sanitization: No sanitization is performed on the ingested file content.
- Context: This ingestion is the primary intended function of the skill and targets local, version-controlled project files.- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a project-specific status command:
openspec show {change-id}. This is a restricted, local operation consistent with the skill's purpose.
Audit Metadata