stelow-workflow-testing-execution
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests external content from live URLs and project source code to perform UX audits and reviews.
- Ingestion points: External website content (Live URL mode in Phase 2) and the local codebase (Phase 4 subagent review).
- Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions when processing external or project content.
- Capability inventory: The skill utilizes shell command execution for testing suites and has file system access to write audit reports to the
.stelow-ux-critique/directory. - Sanitization: Absent; no explicit sanitization, validation, or escaping of ingested external content is mentioned.
- [COMMAND_EXECUTION]: The skill triggers the execution of local development and testing commands, specifically
go test,npm test, andpytest. While this is the intended functionality of a QA skill, it involves executing code within the local environment.
Audit Metadata