openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the 'openspec' CLI tool using the 'list' and 'status' arguments to retrieve metadata about changes and specification paths in JSON format. These operations are scoped to retrieving status and listing available resources.- [PROMPT_INJECTION]: The skill reads and interprets content from external delta specification files to perform merging logic. This data ingestion represents a surface for indirect prompt injection, as the agent is instructed to interpret intended changes from these files.
- Ingestion points: Delta specification files located at paths defined in the 'openspec status' output.
- Boundary markers: Absent; the skill relies on natural language understanding of markdown headers within the processed files.
- Capability inventory: Execution of 'openspec' CLI commands and file system write operations to update main specification files.
- Sanitization: Absent; the skill directly processes the text content of the delta specs to update main files.
Audit Metadata