skills/bitjaru/styleseed/ss-component/Gen Agent Trust Hub

ss-component

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses user-provided descriptions via the $ARGUMENTS variable to guide its code generation process without applying sanitization or boundary markers. This creates an attack surface for indirect prompt injection, where malicious instructions inside a component description could potentially influence the agent's behavior. \n
  • Ingestion points: SKILL.md (via $ARGUMENTS variable). \n
  • Boundary markers: None; user input is interpolated directly into the task instructions. \n
  • Capability inventory: The skill utilizes Write, Edit, and Bash tools to perform project modifications. \n
  • Sanitization: No explicit sanitization, filtering, or validation is performed on the user-provided arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 07:35 PM
Security Audit — agent-trust-hub — ss-component