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) and examples/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
Risk Level
SAFE
Analyzed
Apr 4, 2026, 10:11 PM