note-ai-assistant

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists exclusively of markdown instructions in SKILL.md and does not include any executable scripts or configuration files.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted text from external note content.
  • Ingestion points: The agent accepts untrusted data through the <Document>, <Block>, and <Selection> tags as defined in SKILL.md.
  • Boundary markers: While the skill uses XML-style tags to delimit data layers, it lacks explicit safety instructions directing the agent to ignore any potential commands or instructions embedded within that data.
  • Capability inventory: The skill allows the agent to modify text, translate content, and answer questions based on the provided context.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the input content before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:47 AM
Security Audit — agent-trust-hub — note-ai-assistant