typography-expert

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by utilizing the WebFetch tool to retrieve external web content. This could allow malicious instructions embedded in web pages to influence agent behavior.
  • Ingestion points: WebFetch tool (SKILL.md).
  • Boundary markers: Absent; no delimiters or ignore-instructions are defined for external content.
  • Capability inventory: Read, Write, Edit, and WebFetch (SKILL.md).
  • Sanitization: Absent; no filtering of ingested web content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 06:39 AM