ai-hot
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local script
scripts/fetch_aihot.pyto interact with the news API. The script is written using standard Python libraries (urllib, json) and does not perform any dangerous system operations or privilege escalations. - [EXTERNAL_DOWNLOADS]: The skill fetches content from the domain
aihot.virxact.com. This network activity is documented and central to the skill's primary function of tracking AI hot topics. - [PROMPT_INJECTION]: The instructions in
SKILL.mdare focused on data filtering and output formatting. There are no attempts to bypass safety filters or override system instructions. - [DATA_EXFILTRATION]: No patterns associated with credential harvesting or the exfiltration of sensitive local files were found. The API used does not require authentication, and no secrets are hardcoded.
- [INDIRECT_PROMPT_INJECTION]: As the skill processes external news data, it has an inherent exposure to indirect prompt injection if the source data contains malicious instructions. However, the skill treats the data as information for summarization and filtering rather than executable commands, which is a standard and acceptable risk for this use case.
Audit Metadata