survey-writer

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill definition contains no instructions for network access, sensitive file system operations, or shell command execution.
  • [PROMPT_INJECTION]: Analysis of the instructions shows they are strictly limited to the stated purpose of academic writing and do not attempt to bypass safety guidelines or system prompts.
  • [DATA_EXFILTRATION]: The skill only interacts with local project-specific files (e.g., outlines and paper summaries) and does not contain hardcoded credentials or mechanisms to send data to external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 04:18 PM