skills/zhixunjie/agent-skills/new-llm/Gen Agent Trust Hub

new-llm

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by using unsanitized user arguments (provider, model, base_url) to dynamically construct filesystem paths and Python source code.
  • Ingestion points: User-provided arguments extracted from the $ARGUMENTS variable (SKILL.md).
  • Boundary markers: Absent; there are no instructions to delimit or ignore instructions within the user-provided data.
  • Capability inventory: The skill uses the Write tool to create files on disk and the Glob tool for directory checks (SKILL.md).
  • Sanitization: No validation or escaping logic is defined for handling path traversal characters (e.g., ..) or code injection sequences in the input parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 01:51 AM