openspec-explore
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
openspecCLI to perform project discovery, check change status, and retrieve artifact instructions. It utilizes commands such asopenspec list,openspec status, andopenspec new change. Tool usage is technically restricted to theopenspeccommand prefix. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local filesystem which could contain malicious instructions designed to influence agent behavior.
- Ingestion points: Processes codebase files, project configuration (
openspec/config.yaml), and JSON output from theopenspecCLI tool. - Boundary markers: No specific delimiters or instructions to ignore embedded instructions are defined for the ingested data.
- Capability inventory: The skill possesses the ability to read project files and write markdown artifacts (proposals, designs, specs) to the filesystem via the
openspecCLI. - Sanitization: No explicit sanitization or filtering of external content is performed before it is interpolated into the agent's context.
Audit Metadata