suparank/optimize

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill ingests untrusted article content and has the capability to modify the filesystem, creating a surface for indirect instructions to influence agent behavior.
  • Ingestion points: Article content is read from .claude/suparank-content/[folder]/article.md and templates from ~/.claude/skills/suparank/templates/.
  • Boundary markers: The skill instructions do not define delimiters or specific 'ignore' instructions when processing external article content.
  • Capability inventory: The agent can modify and save files (edit the article file directly and re-save).
  • Sanitization: No sanitization or validation of the ingested article content is performed before processing or editing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 07:37 AM
Security Audit — agent-trust-hub — suparank/optimize