async-python
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external APIs and user-supplied parameters, which creates a potential surface for indirect prompt injection attacks where malicious data could influence agent behavior.
- Ingestion points: External data is retrieved using
aiohttp.ClientSession.getand user input is accepted via FastAPI path parameters inSKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded directives were identified in the implementation examples.
- Capability inventory: The skill demonstrates capabilities for network communication via
aiohttpand database interaction viaasyncpgandSQLAlchemy(SKILL.md). - Sanitization: Database interactions correctly use parameterized queries (e.g.,
$1), which mitigates SQL injection, but the skill does not demonstrate specific sanitization for potential prompt injection within the content fetched from remote sources.
Audit Metadata