agently-triggerflow
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted input data by interpolating it directly into model prompts without specific boundary markers or sanitization, creating a potential surface for indirect prompt injection.
- Ingestion points:
examples/response_fanout.py(data.value) andexamples/stream_bridge.py(data.value). - Boundary markers: Absent. The input is injected using f-strings without delimiters like XML tags or explicit instructions to ignore embedded commands.
- Capability inventory: No file system writes, arbitrary network requests, or subprocess executions were found in the provided Python scripts.
- Sanitization: Absent. Input is used directly as part of the prompt string.
Audit Metadata