py-async
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for fetching data from external network sources, creating a potential attack surface where instructions embedded in external content could influence the agent's behavior.
- Ingestion points:
references/examples.md(Example 2) demonstrates fetching data from external URLs usingaiohttp, andreferences/examples.md(Example 4) illustrates processing streams of external data. - Boundary markers: The instructions do not provide explicit delimiters or "ignore instructions" directives when processing or interpolating data retrieved from external sources.
- Capability inventory: The skill demonstrates network access via
aiohttpandhttpxalong with complex asynchronous task management. - Sanitization: No evidence of data sanitization or input validation is present in the examples provided for processing network response content.
Audit Metadata