openspec-ff-change
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands via the
openspecCLI to manage project state, such as creating new change sets, checking status, and fetching instructions for artifact generation. - [PROMPT_INJECTION]: The skill processes instructions and templates from an external command output (
openspec instructions), creating an indirect prompt injection surface where external data influences the agent's behavior. - Ingestion points: JSON output from
openspec instructions, specifically theinstruction,context,rules, andtemplatefields. - Boundary markers: The skill contains explicit instructions to separate the
contextandrulesfrom the final output, providing a boundary between guiding constraints and generated content. - Capability inventory: The agent has the capability to execute shell commands and write to the local file system.
- Sanitization: There is no explicit sanitization or validation of the CLI output before it is used by the agent to generate new files.
Audit Metadata