manage-seeders

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill establishes a high-risk attack surface by instructing the agent to ingest untrusted external data and use it for high-privilege side effects.
  • Ingestion points: External data enters the agent context via database/data/*.json files (SKILL.md).
  • Boundary markers: The skill fails to provide delimiters or instructions to ignore embedded commands within the JSON data, leaving the agent vulnerable to instructions contained within the data files.
  • Capability inventory: The skill uses file_get_contents for file access and updateOrCreate for database writes (SKILL.md).
  • Sanitization: There are no sanitization, escaping, or schema validation steps described to prevent malicious data or instructions from being processed.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 05:46 AM