community-notes

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill references an external Javascript file src/communityNotes.js which contains the actual logic but was not provided for security review.
  • [SAFE]: The documentation and configuration patterns are consistent with the stated purpose of managing Community Notes via browser automation.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from X.com.
  • Ingestion points: The skill reads tweet text and existing Community Notes directly from the browser DOM at x.com via the src/communityNotes.js script.
  • Boundary markers: Absent. There are no instructions to the agent to ignore or delimit embedded commands within the fetched content.
  • Capability inventory: Performs DOM manipulation and browser-based actions (view, write, rate) on x.com.
  • Sanitization: Absent. No explicit sanitization or validation of the ingested content is described in the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:43 PM
Security Audit — agent-trust-hub — community-notes