openspec-ff-change
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the 'openspec' command-line interface to create, track, and manage project changes. It executes commands such as 'openspec new', 'openspec status', and 'openspec instructions' to automate the workflow based on user input.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external CLI outputs and existing project files to generate new content. Ingestion points: Instructions, rules, and project metadata are read from JSON outputs and dependency files at runtime. Boundary markers: The skill instructs the agent to treat 'context' and 'rules' as constraints rather than content but lacks formal structural markers to isolate this untrusted data from the generation process. Capability inventory: The skill can execute shell commands and perform file operations to create and modify the project structure. Sanitization: No explicit sanitization or validation of the ingested data is described before it is used to influence the agent's behavior and output.
Audit Metadata