frontend-checklist-global

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because its core functionality requires processing untrusted external data.
  • Ingestion points: Data enters the context via the audit_url tool (fetching remote HTML) and the review_code tool (processing user-provided snippets) as described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or explicit boundary markers to isolate analyzed code from the agent's instructional logic.
  • Capability inventory: The skill's capabilities are focused on network retrieval of public pages and rule-based auditing; it does not include instructions for direct system command execution or sensitive local file access.
  • Sanitization: There is no evidence of sanitization or content validation for the ingested external data before processing.
  • [SAFE]: All external URLs and references (e.g., to frontendchecklist.io) target official vendor domains and documentation, appearing consistent with the skill's intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:19 PM
Security Audit — agent-trust-hub — frontend-checklist-global