learning-notes-organizer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text from user-specified Markdown files, which creates a vulnerability to indirect prompt injection where malicious instructions inside the notes could be executed by the agent during the refactoring process.
- Ingestion points: The text content of the user-provided file defined by the
target_fileparameter. - Boundary markers: The skill does not implement delimiters or 'ignore' instructions to prevent the agent from following commands embedded within the input data.
- Capability inventory: Across its scripts, the skill performs file reading and file writing (specifically creating scaffold Markdown files).
- Sanitization: The instructions do not mandate any escaping or validation of the input content before interpolation into the agent's context.
Audit Metadata