quality-expert
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted user-supplied data, such as testing strategies, architecture descriptions, and flaky test reports, creating a vulnerability surface for indirect prompt injection attacks.
- Ingestion points: The skill activates when evaluating, reviewing, or designing testing strategies and architectures provided by the user in SKILL.md.
- Boundary markers: The instructions do not include specific delimiters, XML tags, or 'ignore embedded instructions' warnings to distinguish user-provided data from agent commands.
- Capability inventory: The skill utilizes filesystem read tools (Read, Glob, Grep) and network search/fetch tools (WebSearch, WebFetch, mcp__scout__navigate, mcp__scout__observe).
- Sanitization: No input sanitization, schema validation, or content filtering mechanisms are defined for the data being processed.
- [SAFE]: No obfuscation (Base64, zero-width characters, or homoglyphs) was found. The skill does not contain hardcoded credentials, persistence mechanisms, or unauthorized command execution patterns. All referenced methodologies and tools (e.g., Vitest, Playwright, Pact, k6) are standard industry resources.
Audit Metadata