minto

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection and HTML injection. It ingests untrusted data (user-provided drafts or ideas) from the conversation history and interpolates it into a visual HTML template.
  • Ingestion points: User-provided drafts or topics extracted from the conversation (SKILL.md).
  • Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore embedded instructions in the processed text.
  • Capability inventory: The skill has the capability to write files (HTML artifacts) to the user's workspace or output folder (SKILL.md).
  • Sanitization: Absent. The skill lacks instructions to sanitize, escape, or validate the user-provided content before it is placed into HTML placeholders like {{LEVEL_1_ANSWER}} or {{EVIDENCE_N}}, which could allow malicious scripts or HTML tags to be executed if the report is opened in a browser.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 02:25 PM
Security Audit — agent-trust-hub — minto