xhtml-author

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its file-editing capabilities.
  • Ingestion points: The skill uses Read, Edit, and Grep tools to interact with existing markup files as described in the allowed-tools metadata.
  • Boundary markers: There are no explicit instructions or delimiters defined in the skill documentation to prevent the agent from following instructions that might be embedded within the files it processes.
  • Capability inventory: The skill is permitted to use Read, Write, Edit, Glob, and Grep tools, allowing for significant file system modification based on interpreted content.
  • Sanitization: The instructions do not specify any sanitization or validation routines for external content before it is processed or used to generate new markup.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 06:11 AM