writing-webdriverio-code
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external website analysis files (e.g.,
references/website-analysis/<target>/website-analysis.md). This creates an indirect prompt injection surface where instructions potentially hidden within the analyzed site content could influence the generated test code. - Ingestion points:
SKILL.md(Project Context Files section) - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the analysis files are defined.
- Capability inventory: The skill's primary capability is generating and modifying test code files.
- Sanitization: There are no explicit instructions for sanitizing or filtering the content retrieved from analysis files.
- [SAFE]: The skill explicitly promotes security best practices by instructing the agent to never hardcode secrets, mask sensitive values during input, and avoid leaking credentials in logs.
Audit Metadata