skills/jbrukh/skills/optimize-prompt/Gen Agent Trust Hub

optimize-prompt

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill includes a 'FIRST-TOKEN CONSTRAINT' to strictly define the agent's output format. This is a common instructional design pattern and does not constitute a malicious override of safety guidelines.\n- [PROMPT_INJECTION]: The skill processes external text via the '{{P}}' variable, which is a surface for indirect prompt injection.\n
  • Ingestion points: External prompt content is provided through the '{{P}}' placeholder in SKILL.md.\n
  • Boundary markers: The input is demarcated by a plain text header without specialized escaping or 'ignore instructions' delimiters.\n
  • Capability inventory: The skill is limited to text analysis and generation; it has no access to the file system, network, or shell commands.\n
  • Sanitization: No validation or sanitization is applied to the input prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:57 AM