azure-functions-devsec
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for functions that process untrusted data from external sources, which is a standard surface area for indirect prompt injection.
- Ingestion points: Data enters the agent context via
req.route_params,req.get_json(), andmsg.get_body()in the Python and Node.js examples withinSKILL.md. - Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are included in the provided code snippets to isolate data from logic.
- Capability inventory: The functions are limited to logging (
logging.info,context.log) and returning responses; no high-risk capabilities like arbitrary command execution or local file system writes are present in the snippets. - Sanitization: The examples include basic JSON validation and checks for required parameters, which are good practices but do not fully mitigate adversarial prompt injection.
Audit Metadata