enrich-notes-loop
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill defines a loop that reads contents of various files in the
raw/directory and vault root. This creates a surface for indirect prompt injection where instructions hidden in the processed files could hijack the agent's behavior during the enrichment process. - Ingestion points: Notes located in the
raw/directory and vault root, as well as thetags.mdregistry file. - Boundary markers: No delimiters or instructions are provided to help the agent distinguish its primary instructions from the content of the notes it processes.
- Capability inventory: The skill iterates through files, reads content, and triggers the
enrich-noteskill, which likely involves writing updates back to the vault. - Sanitization: No sanitization of note content is mentioned before processing.
- [NO_CODE]: The skill consists entirely of natural language instructions and references to other skills, with no internal scripts or executable code.
Audit Metadata