tdp-plugin-restore

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill relies on user-provided plugin names to construct local and external file paths without sanitization or validation.
  • Ingestion points: Plugin name extracted from user request in SKILL.md.
  • Boundary markers: None identified.
  • Capability inventory: Recursive directory deletion and recursive file copying in SKILL.md.
  • Sanitization: No input validation or path sanitization is mentioned. A malicious plugin name (e.g., including path traversal sequences like ../) could result in unauthorized file deletion or overwriting of sensitive data outside the intended plugin directories.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:38 PM
Security Audit — agent-trust-hub — tdp-plugin-restore