openspec-sync-specs
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
openspecCLI tool to fetch change data via the commandopenspec list --json. This is an expected operation for a skill designed to interact with this specific CLI. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external markdown files (delta specs) to update main specs.
- Ingestion points: The agent reads files located at
openspec/changes/<name>/specs/*/spec.md. - Boundary markers: Absent; the instructions do not specify the use of delimiters when reading the specification files.
- Capability inventory: The skill is limited to reading and writing markdown files within the project directory and executing specific
openspecCLI commands. - Sanitization: Absent; the content from the delta specs is intelligently merged into the main specifications by the agent without explicit sanitization steps.
Audit Metadata