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, and WebSearch tools.
  • Sanitization: No sanitization or validation of the research abstract is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 04:11 AM
Security Audit — agent-trust-hub — tw-research-journal-selector