openspec-explore
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from the local codebase, project configuration files, and CLI output which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The agent reads local codebase files, project-specific configuration (openspec/config.yaml), and existing OpenSpec artifacts (proposals, designs, specs).
- Boundary markers: The skill instructs the agent to treat rules as constraints but lacks explicit delimiters or protective framing for untrusted data processed during exploration.
- Capability inventory: The agent has the capability to list, read, and write project-related artifacts using the openspec CLI tool.
- Sanitization: No sanitization or validation of external file content is performed before it enters the agent's reasoning process.
- [COMMAND_EXECUTION]: The skill utilizes the openspec CLI to interact with the project repository and manage specifications.
- Evidence: The skill instructions involve executing openspec subcommands like list, new change, status, and instructions to manage project state and capture exploration insights.
Audit Metadata