openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
openspec list --jsoncommand to retrieve available changes. This command is a core part of the skill's functionality and interacts with the project-specific 'openspec' CLI. - [PROMPT_INJECTION]: The skill processes content from 'delta spec' Markdown files to update main specifications, which introduces a surface for indirect prompt injection.
- Ingestion points: Data is read from files located at
openspec/changes/<name>/specs/*/spec.mdas described in SKILL.md. - Boundary markers: Absent; the instructions direct the agent to read and interpret the files directly without specific delimiters or isolation.
- Capability inventory: The agent is authorized to read, create, and modify files within the
openspec/directory structure. - Sanitization: No validation or sanitization of the specification content is mentioned; the agent relies on 'intelligent merging' to apply changes.
Audit Metadata