create-user-stories

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses a template that incorporates user-provided content via the $ARGUMENTS variable, which creates a surface for indirect prompt injection.\n
  • Ingestion points: SKILL.md (context interpolated from user input).\n
  • Boundary markers: Input is delimited by tags to distinguish it from the agent's instructions.\n
  • Capability inventory: None. The skill consists solely of prompt instructions and does not utilize tools, scripts, or network access.\n
  • Sanitization: No explicit sanitization or filtering is performed on the input content.\n- [NO_CODE]: The skill package does not contain any scripts, binaries, or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 06:49 PM
Security Audit — agent-trust-hub — create-user-stories