openspec-ff-change
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
openspecCLI to manage project state and generate files. It executes specific subcommands likeopenspec new change,openspec status, andopenspec instructionsto retrieve project metadata and instructions. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user descriptions and CLI tool outputs (JSON). This represents a potential surface for indirect prompt injection if the inputs contain instructions. However, the skill mitigates this by using structured data fields (
template,instruction,rules) to guide the agent's output rather than executing the raw input as code.
Audit Metadata