lead-architect

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (HIGH): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it ingests untrusted web content and possesses file-writing capabilities.
  • Ingestion points: Rule 1 requires using the search_web tool for current architectural research.
  • Boundary markers: There are no delimiters or instructions provided to isolate or ignore embedded commands within the web-retrieved data.
  • Capability inventory: Rule 6 allows the agent to use write_to_file to generate technical artifacts like ADRs, RFCs, and SDDs.
  • Sanitization: No sanitization, validation, or escaping of external content is performed before it is incorporated into the generated file artifacts.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 05:20 AM