frontend-security-coder
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill files confirms they consist strictly of markdown-based instructions and implementation guidelines for frontend security. No executable code, shell scripts, or system-level commands are included within the skill package.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as its primary function is to process untrusted data such as user-generated HTML and cross-window messages.
- Ingestion points: Untrusted content types (text, HTML, URLs) are explicitly identified in
resources/implementation-playbook.md. - Boundary markers: The instructions mandate the use of established sanitizers and provide specific rendering preferences (e.g.,
textContent). - Capability inventory: No automated tools, subprocess calls, or network-active scripts are defined in the skill files.
- Sanitization: The skill explicitly enforces the use of
textContentandDOMPurifyto sanitize dynamic content, effectively mitigating the risk of executing injected payloads. Given the instructional context and lack of exploitable tools, this is categorized as safe.
Audit Metadata