classical-japanese-literature-guide
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The
modules/research-checklist.mdfile instructs the agent to ingest and process data from external, untrusted sources such as Wikipedia and ArXiv using research tools. This creates an indirect prompt injection surface. - Ingestion points: Web research and distillation tool results referenced in
modules/research-checklist.md. - Boundary markers: No specific instructions or delimiters are provided to handle external content as untrusted.
- Capability inventory: The skill consists of static markdown files and does not contain scripts with subprocess, file-write, or network capabilities.
- Sanitization: No evidence of sanitization or validation of the ingested external content is present.
Audit Metadata