mom-test

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses the $ARGUMENTS placeholder to insert untrusted user content directly into the prompt context, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided text such as ideas, interview questions, or transcripts is ingested through the $ARGUMENTS variable in SKILL.md.
  • Boundary markers: The skill uses XML-style tags to delimit user input, providing a basic level of instruction/data separation.
  • Capability inventory: The skill performs only text generation and has no access to tools or scripts for network communication, file system modification, or command execution.
  • Sanitization: No sanitization or escaping of the user-provided content is performed before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:29 PM
Security Audit — agent-trust-hub — mom-test