302ai-api-integration
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [Indirect Prompt Injection] (MEDIUM): The skill ingests untrusted external data which could contain malicious instructions. * Ingestion points:
scripts/parse_api_list.pyfetches content fromhttps://doc.302.ai/llms.txt. * Boundary markers: Absent. * Capability inventory: The agent uses this data to recommend APIs and generate source code for the user, which could be influenced by malicious content in the fetched list. * Sanitization: Limited to basic regex parsing inparse_llms_txt. - [Data Exposure & Exfiltration] (LOW): The skill performs network operations to an external domain (
doc.302.ai) which is not on the trusted sources list. Evidence:requests.getinscripts/parse_api_list.py. - [Unverifiable Dependencies] (LOW): The skill relies on the
requestslibrary for Python as documented inreferences/parse_script_usage.md.
Audit Metadata