k-research-note
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
- Ingestion points: Untrusted data enters the context through user-provided files (CSV, JSON, XML, and logs) processed by
scripts/data_processor.pyin Step 5-2. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the data contents passed to the AI during generation steps.
- Capability inventory: The skill uses
web_searchand can write files to the system viascripts/generate_note.py. - Sanitization: There is no evidence of content sanitization or validation of the data files before processing.
Audit Metadata