deep-research-report
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a text-processing utility that lacks capabilities for sensitive file access, persistent network connections, or unauthorized command execution.
- [SAFE]: The instructions include a 'no-addition' principle (盛らない原則), which serves as a safety constraint by requiring the agent to verify all outputted data against the provided source material to prevent hallucinations.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted research data, but the attack surface is mitigated by the lack of downstream capabilities (no file writing or shell access) and an explicit requirement to maintain data integrity and ignore external biases.
- [SAFE]: The installation instructions and asset references point to the author's own verified repository, presenting no evidence of typosquatting or malicious redirection.
Audit Metadata