AI Researcher
Pass
Audited by Gen Agent Trust Hub on Feb 13, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious patterns, prompt injection attempts, or obfuscated content were detected in the skill files.
- [NO_CODE] (SAFE): The skill consists entirely of Markdown instructions and metadata. It does not contain any Python scripts, Node.js code, shell scripts, or other executable components.
- [Indirect Prompt Injection] (INFO): The skill is designed to synthesize research on external topics, which inherently involves processing untrusted data. Evidence Chain: 1. Ingestion points: User-provided research topics (SKILL.md). 2. Boundary markers: Absent; there are no instructions to delimit or ignore instructions within researched content. 3. Capability inventory: The skill is restricted to generating text formatting and has no access to subprocesses, file-system writing, or network operations. 4. Sanitization: None present. Severity is INFO because the skill is limited to 'display only' functionality.
Audit Metadata