exploring-llm-traces

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing and displaying untrusted data from external AI traces.
  • Ingestion points: The skill uses posthog:query-llm-trace and posthog:query-llm-traces-list to fetch trace data, which includes external LLM inputs, outputs, and system prompts. This data is then read by the scripts in the scripts/ directory.
  • Boundary markers: The trace content is printed by the parsing scripts and interpreted by the agent without explicit boundary delimiters or warnings to ignore embedded instructions.
  • Capability inventory: The agent is authorized to execute shell commands (to run the provided Python scripts) and can perform arbitrary database queries via the posthog:execute-sql tool.
  • Sanitization: The provided Python scripts (e.g., extract_conversation.py) include logic to truncate long strings for display purposes but do not perform security-focused sanitization or escaping of the retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 08:16 PM