expert-advice

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates user input via the $ARGUMENTS variable directly into its instructions without the use of delimiters or protective boundary markers, creating a surface for indirect prompt injection.
  • Ingestion points: $ARGUMENTS in SKILL.md
  • Boundary markers: Absent
  • Capability inventory: Filesystem read (codebase exploration) and network fetch (Wasp documentation)
  • Sanitization: Absent
  • [EXTERNAL_DOWNLOADS]: The skill retrieves documentation from external sources to provide context-aware advice on application improvements.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 06:12 PM