note-title-reviewer

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows its stated purpose of reviewing article titles and does not exhibit any malicious behaviors such as data exfiltration, command execution, or persistence.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted external content. \n
  • Ingestion points: External article content is fetched via browser_navigate in SKILL.md.\n
  • Boundary markers: None identified; untrusted content is processed directly alongside instructions.\n
  • Capability inventory: Uses Read, browser_navigate, and browser_snapshot. No file-write or shell execution tools are available to the skill.\n
  • Sanitization: No evidence of content filtering or sanitization before processing.- [EXTERNAL_DOWNLOADS]: No external packages or remote scripts are downloaded or executed.- [CREDENTIALS_UNSAFE]: No hardcoded credentials or sensitive file paths were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 02:50 PM