ai-researcher
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown files (
SKILL.mdand reference documents). It contains no scripts (Python, JavaScript, shell), binaries, or automation code. - [SAFE]: No malicious patterns, prompt injections, or exfiltration vectors were detected. The skill provides methodologies for academic and industrial research framing, literature synthesis, and benchmarking.
- [INDIRECT_PROMPT_INJECTION]: While the skill workflows involve processing external content such as research papers (ingestion point in
SKILL.md), it lacks any executable capabilities, network tools, or file-write permissions that could be exploited through such data. It focuses on manual synthesis and reporting rather than automated tool execution based on external data.
Audit Metadata