tw-research-journal-selector
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and reference data are consistent with its stated purpose of academic journal recommendation. No malicious code, obfuscation, or persistence mechanisms were detected. References to external government websites (nstc.gov.tw) are for data verification and originate from trusted official sources.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to how it processes user-provided research abstracts alongside high-capability tools.
- Ingestion points: User-provided research abstract in
SKILL.md(Step 2, Q1). - Boundary markers: Absent. The skill does not use delimiters or explicit instructions to the agent to ignore potentially malicious directives embedded in the abstract.
- Capability inventory: The skill utilizes
Bash,Write, andWebSearchtools. - Sanitization: No sanitization or validation of the research abstract is performed before processing.
Audit Metadata