curate
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the
Inbox/directory. Maliciously crafted notes could attempt to influence the agent's behavior during the curation process. - Ingestion points: Fleeting notes read from the
Inbox/folder (SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when processing note content.
- Capability inventory: File system access including reading, writing, moving, and deleting files within the
~/second-brain/directory tree (SKILL.md). - Sanitization: The skill lacks explicit sanitization or filtering of note content before it is processed by the agent.
Audit Metadata