research-paper-writer
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The
index.jsfile is a boilerplate placeholder that does not perform any functional logic or risky operations. - [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process user-provided research materials, which could contain malicious instructions. 1. Ingestion points:
SKILL.md(Workflow Step 1.2: 'Review any provided research materials'). 2. Boundary markers: Absent. The instructions do not define delimiters or warnings to ignore instructions inside research data. 3. Capability inventory: None. The skill scripts lack network, file system, or execution capabilities. 4. Sanitization: Absent. No filtering or validation of input data is described.
Audit Metadata