opsx-solve-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands via Bash to perform engineering verification tasks, including running test suites (
npm test,pytest,go test), linters, and build processes. It also invokes OpenSpec CLI tools (e.g.,openspec validate) for artifact validation. These operations are essential for the skill's primary function of solving engineering problems and verifying the results. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from user-provided problem descriptions, codebases, and external links (such as Figma URLs). The risk of indirect prompt injection is mitigated by the skill's architectural design, which includes active questioning to resolve ambiguity, multiple human-in-the-loop confirmation gates in manual mode, and mandatory verification stages that check implementation against design specs before completion.
Audit Metadata