frontend-interviewer

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill consists entirely of markdown documentation (SKILL.md, references/frontend-knowledge.md) and does not contain any executable scripts, binaries, or system commands.
  • [Indirect Prompt Injection] (SAFE): The skill is designed to process untrusted user data (resumes) as its primary input.
  • Ingestion points: Resume content (text or files) provided by the user in SKILL.md Step 1.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) for the user-provided resume.
  • Capability inventory: Restricted to text-based role-play. The skill does not have capabilities for network access, file system modifications, or arbitrary code execution.
  • Sanitization: No sanitization or filtering is applied to the input. While vulnerable to data-driven instruction overrides, the lack of dangerous capabilities mitigates the risk to a SAFE level.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 08:41 PM