journal-entry
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input and can export formatted content to external note-taking tools.
- Ingestion points: User free writing and prompt responses (SKILL.md).
- Boundary markers: The skill does not define explicit technical delimiters for user input, using standard Markdown headings for output structure.
- Capability inventory: The skill is instructed to save notes to external applications using the Scratchpad connector or other note tools (SKILL.md).
- Sanitization: The instructions provide a safeguard by requiring the agent to preserve the user's original words, slang, and swearing while strictly prohibiting interpretation, advice, or new content generation.
Audit Metadata