openspec-continue-change
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes openspec CLI commands to track progress and retrieve artifact-specific instructions. These commands are necessary for the skill's primary function and are executed within the user's local environment.
- [PROMPT_INJECTION]: The skill processes JSON output and local files to determine artifact content, creating a surface for indirect prompt injection. 1. Ingestion points: JSON output from openspec status and openspec instructions commands, as well as dependency files read from disk. 2. Boundary markers: The skill includes explicit instructions to treat context and rules fields as background constraints rather than content for the output file. 3. Capability inventory: The skill has permission to execute openspec CLI commands and write files to the resolvedOutputPath determined by the tool. 4. Sanitization: No specific input sanitization is performed on the data fields, as the skill relies on the structure of the tool-generated JSON.
Audit Metadata