bahasa-peneliti
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and contains no executable code, scripts, or binary files across its documentation and reference materials.
- [SAFE]: It implements proactive safety measures against data integrity issues (hallucination) by instructing the agent to use explicit markers like
[RUJUKAN DIPERLUKAN]for missing references instead of fabricating citations. - [SAFE]: No external network requests, sensitive file access, or administrative command executions were detected in the instructions or references.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes user-supplied manuscripts and research data. However, the risk is negligible because the skill does not request access to any dangerous tools (e.g., shell, network, or file-write capabilities) that could be exploited to cause harm.
Audit Metadata