skills/terminalskills/skills/langfuse/Gen Agent Trust Hub

langfuse

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill documents the use of Langfuse's prompt management features, which involve fetching prompt templates from a remote server and interpolating variables. This creates an indirect prompt injection surface.
  • Ingestion points: Remote prompt templates fetched via langfuse.get_prompt() in SKILL.md.
  • Boundary markers: Absent in the provided examples.
  • Capability inventory: Orchestrates LLM generations via the openai library as shown in SKILL.md.
  • Sanitization: No explicit sanitization or validation of the fetched prompt content or interpolation variables is demonstrated.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 09:15 PM