career-resume

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains explicit instructions to help users "bypass" or "evade" AI-generated text detection systems (e.g., "AI 진정성 검증 회피 가드"). While this is intended to help candidates pass HR filters by refining text rhythm and tone, it involves instructions that teach the model how to circumvent specific content classifiers.
  • [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and processing untrusted external data, such as job descriptions (JD) and career histories provided by the user. This creates a surface where instructions embedded in a JD or history could potentially influence the agent's behavior.
  • Ingestion points: User-supplied career details and job descriptions processed via SKILL.md.
  • Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore potentially adversarial commands within the ingested data.
  • Capability inventory: The skill utilizes text generation and the mcp__sequential-thinking__sequentialthinking tool for multi-step reasoning.
  • Sanitization: The skill does not define specific methods for filtering or sanitizing the input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:42 PM
Security Audit — agent-trust-hub — career-resume