note-taking

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection during the synthesis and retrieval phase.
  • Ingestion points: The agent processes and summarizes content from Markdown files stored in a user-defined directory, as specified in SKILL.md.
  • Boundary markers: The instructions do not define clear delimiters or include 'ignore embedded instructions' directives when the agent is asked to synthesize information from existing notes.
  • Capability inventory: The skill utilizes file system read/write operations and provides the agent with the ability to search and summarize stored content.
  • Sanitization: There is no mention of sanitizing or escaping the content of notes before they are interpolated into the agent's context for summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 12:01 PM
Security Audit — agent-trust-hub — note-taking