skills/posthog/skills/signals/Gen Agent Trust Hub

signals

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to ingest and process natural language content from the document_embeddings table.\n
  • Ingestion points: Data is fetched from the content and metadata columns of the document_embeddings table via the posthog:execute-sql tool.\n
  • Boundary markers: The instructions do not include specific delimiters or warnings to disregard instructions embedded within the fetched signal data.\n
  • Capability inventory: The agent utilizes the posthog:execute-sql tool and processes the natural language output.\n
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from the database before processing.\n- [COMMAND_EXECUTION]: The skill provides SQL query templates for use with the posthog:execute-sql tool to interact with the database environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 09:04 AM