skills/junhyunny/skills/proofread/Gen Agent Trust Hub

proofread

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests and processes the full content of external files without utilizing delimiters or boundary markers to distinguish content from instructions.
  • Ingestion points: Reads the entire content of the file located at the user-supplied PATH.
  • Boundary markers: Absent. The instructions do not include markers or warnings to ignore potentially malicious commands embedded within the processed document.
  • Capability inventory: The skill is authorized to read and overwrite local files to apply corrections and update metadata.
  • Sanitization: None. No input validation or filtering is performed on the file content before it is processed for corrections.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:24 AM