developer-assessment-evaluator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): Vulnerability to indirect prompt injection via untrusted candidate code. Ingestion points: The skill ingests user-provided coding assessments and take-home projects as described in SKILL.md. Boundary markers: Absent; there are no specified delimiters or instructions to ignore embedded commands within the candidate submissions. Capability inventory: The skill utilizes local scripts scripts/detect-trivia.py and scripts/score-assessment.py for its core functionality. Sanitization: No evidence of input sanitization or filtering of external code submissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:40 PM