langfuse
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for tracing and logging LLM interactions, creating an ingestion surface for potentially untrusted data.
- Ingestion points: Data enters the system via
inputandoutputparameters in methods such astrace.generation()andgeneration.end()in SKILL.md. - Boundary markers: The provided code snippets do not include explicit delimiters or instructions to ignore embedded commands within the logged content.
- Capability inventory: The skill utilizes network capabilities to transmit logged data to the Langfuse host and interacts with LLM providers like OpenAI and LangChain.
- Sanitization: No explicit sanitization or filtering of the LLM outputs is demonstrated before they are sent to the observability platform.
Audit Metadata