skills/brycewang-stanford/awesome-journal-skills/earth-and-planetary-science-letters/Gen Agent Trust Hub
earth-and-planetary-science-letters
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing heuristics and guidelines for the AI agent to evaluate research papers. It contains no executable scripts, shell commands, or network exfiltration logic.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for processing untrusted data (user manuscript content) in
SKILL.md. However, it includes no dangerous capabilities, command executions, or network operations that could be exploited via injection. It functions strictly as an analytical and formatting assistant. - Ingestion points: User-provided research descriptions or manuscript drafts analyzed according to the guidelines in
SKILL.md. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No subprocess calls, file-write operations, or network exfiltration patterns found in the skill text.
- Sanitization: None present; the skill relies on the agent's core safety layers.
Audit Metadata