ai-flavor-detector

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it processes untrusted user text for analysis. Maliciously crafted text could attempt to subvert the agent's instructions.
  • Ingestion points: Text ingested via the Read tool or direct user input.
  • Boundary markers: There are no defined delimiters to isolate the text being analyzed.
  • Capability inventory: The skill utilizes Write and Edit tools which could be targeted by an injection attack.
  • Sanitization: No sanitization of the input text is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 02:19 AM