openspec-ff-change

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the openspec command-line interface to manage project schemas, create new change directories, and query change status. These operations are core to the skill's functionality as a development automation tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, including project configuration files (openspec/config.yaml), CLI status reports (JSON format), and artifact templates. This content influences the generation of implementation tasks and design documents. The ingestion process includes: 1. Ingestion points: Reads from project config, CLI JSON output, and template files. 2. Boundary markers: None specified. 3. Capability inventory: Command execution via openspec and file writing via TodoWrite. 4. Sanitization: Kebab-case conversion for change names, but no explicit sanitization for template content. While this represents a surface for indirect instruction processing, the activity is confined to the local project context and standard developer workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 08:20 PM
Security Audit — agent-trust-hub — openspec-ff-change