evidence-draft
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs local data transformation on research artifacts (notes, briefs, and citations) and does not possess network capabilities or external dependencies.
- [SAFE]: The main execution logic in
scripts/run.pyis deterministic and avoids unsafe dynamic execution patterns likeeval,exec, or direct shell command invocation. - [SAFE]: Robust input sanitization is performed by the
_sanitize_source_textfunction, which applies hygiene regex patterns to remove URLs, self-narration, and boilerplate content from paper snippets. - [SAFE]: The skill manages potential indirect prompt injection risks by sanitizing external content before it is structured into packs for downstream use.
- [SAFE]: The skill adheres to strict validation rules and an explicit schema for its JSONL outputs, ensuring predictable behavior within the agent environment.
Audit Metadata