managing-streamlit-apps

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill is designed to facilitate the deployment and runtime execution of Python code within a PostHog sandbox environment via the streamlit-apps-set-source and streamlit-apps-start tools. This behavior is the intended primary functionality of the skill and is documented with appropriate resource limits and lifecycle controls.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a toolset for piping application source code strings into a execution environment. While this creates a potential surface for indirect prompt injection if an agent interpolates untrusted data into the source code, the skill is focused on authenticated administrative tasks within the vendor's platform.
  • Ingestion points: streamlit-apps-set-source in SKILL.md accepts application source code as a string.
  • Boundary markers: None explicitly mentioned in the skill instructions.
  • Capability inventory: Includes tools to create, update, start, and stop sandboxed applications.
  • Sanitization: Relies on the platform's internal sandbox isolation and authentication mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:58 AM
Security Audit — agent-trust-hub — managing-streamlit-apps