deep-research
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and reference templates. It defines a multi-step workflow for research and report generation including intake, planning, evidence collection, triage, and drafting.
- [NO_CODE]: The skill does not include any executable scripts, binary files, or external dependencies. It relies on the agent's built-in tools (e.g.,
deepresearch,Task) and standard markdown processing. - [SAFE]: The file
.security-scan-passedappears to be a metadata file from a prior automated scan. While not an authoritative claim for the current analysis, its presence is noted and it contains no malicious instructions. - [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface (Step 3: Evidence Collection) where it gathers external data. However, the instructions include strict source triage (Step 4), quality rubrics, and verification checklists (Step 8) to mitigate risks associated with untrusted external content. Findings for this category are assessed as safe due to these robust guardrails and standard research use case.
Audit Metadata