khazix-title
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The scripts
fetch_list.pyandfetch_meta.pyperform network requests tojintiankansha.comto scrape article titles and publication times. This activity is documented as part of the data collection process and is intended to be run locally by the user to build the reference library. The domains accessed are consistent with the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill operates by analyzing user-provided article drafts or summaries to suggest titles. This process involves handling external, untrusted content which is a standard surface for indirect prompt injection. However, the risk is mitigated by the skill's highly constrained output format and lack of high-privilege execution tools.
Audit Metadata