molten-validate
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input which is later persisted in the local workspace.
- Ingestion points: User input is gathered through initial pitches and the five-round interview process defined in SKILL.md and references/full-interview.md.
- Boundary markers: Present; the references/report-template.md uses Markdown headers and blockquotes to provide structural separation for user-provided answers.
- Capability inventory: The skill requires file system access to create directories and write Markdown files as specified in references/report-template.md.
- Sanitization: Absent; the instructions do not include specific steps to escape or sanitize user input before it is written to the report files.
Audit Metadata