posthog-debugger

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites, creating a surface for potential indirect prompt injection where a site could attempt to influence the agent's behavior.\n
  • Ingestion points: The skill reads page titles, accessibility trees, and console logs using mcp__chrome-devtools__take_snapshot, mcp__chrome-devtools__list_console_messages, and mcp__playwright__browser_snapshot as defined in SKILL.md.\n
  • Boundary markers: There are no explicit delimiters or instructions to ignore instructions found within the processed website content or logs.\n
  • Capability inventory: The agent has the ability to navigate to arbitrary URLs, list network requests, and execute JavaScript via evaluate_script tools in SKILL.md.\n
  • Sanitization: The skill does not implement specific sanitization or filtering for website-provided text before processing.\n- [DYNAMIC_EXECUTION]: The skill uses browser automation to execute JavaScript snippets on the global state of target websites. While the code templates are defined within the skill, they interact directly with the runtime environment of untrusted websites.\n
  • Evidence: Use of mcp__chrome-devtools__evaluate_script and mcp__playwright__browser_evaluate in SKILL.md to run custom diagnostic code in the browser context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:47 AM
Security Audit — agent-trust-hub — posthog-debugger