astrophysical-journal-letters

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's instructions are focused entirely on scientific venue selection and journal policy compliance. No obfuscation, malicious network activity, or credential theft patterns were found.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted manuscript data provided by users.
  • Ingestion points: The agent reads user manuscripts to evaluate them against the criteria in SKILL.md.
  • Boundary markers: There are no explicit instructions for the agent to use delimiters or to disregard instructions contained within the user-supplied manuscript.
  • Capability inventory: The skill is limited to providing scientific analysis and reading internal reference files (source-basis.md, official-source-map.md).
  • Sanitization: The skill does not implement sanitization or filtering of the incoming manuscript content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 02:57 AM
Security Audit — agent-trust-hub — astrophysical-journal-letters