research
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill requests 'network:http' and 'file:write' permissions, which are consistent with its stated purpose of performing online research and saving documentation to a 'research/' directory.
- [SAFE]: The instructions do not contain any prompt injection patterns, obfuscation, or attempts to bypass agent safety guidelines.
- [SAFE]: Analysis of the skill reveals an indirect prompt injection surface because it processes untrusted data from external websites.
- Ingestion points: External academic and data sources accessed via network tools (SKILL.md).
- Boundary markers: Absent; there are no specific instructions to the agent to ignore potentially malicious commands within the sourced text.
- Capability inventory: The agent has 'file:write' access to the local filesystem (SKILL.md).
- Sanitization: Absent; the skill summarizes content and saves it to a citation format without explicit sanitization steps.
Audit Metadata