opsx-apply
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
openspecandcodegraphCLI tools to retrieve task status, fetch implementation instructions, and synchronize the codebase. - [PROMPT_INJECTION]: The skill is designed to process output from external CLI tools to guide its actions, which constitutes a standard indirect prompt injection surface for automation tools.
- Ingestion points: Output from
openspec status,openspec instructions apply, andcodegraph explore. - Boundary markers: The skill does not define explicit delimiters for content ingested from these tools.
- Capability inventory: Includes the execution of project-specific CLI tools and management of task completion states.
- Sanitization: The skill relies on the output of trusted development tools without implementing additional internal filtering.
Audit Metadata