skills/brycewang-stanford/awesome-journal-skills/nature-reviews-earth-and-environment/Gen Agent Trust Hub
nature-reviews-earth-and-environment
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists solely of Markdown text and YAML frontmatter, providing instructions to an AI agent without any accompanying executable scripts or binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data for verification. 1. Ingestion points: References to local resource files (
source-basis.md,official-source-map.md) and instructions to search the live web for author guidelines. 2. Boundary markers: None present. 3. Capability inventory: The skill contains no scripts, subprocesses, or network writing capabilities. 4. Sanitization: None present. Because the skill lacks any privileged capabilities, this ingestion surface does not pose a functional risk. - [SAFE]: The skill follows standard practices for a writing assistant and contains no evidence of prompt injection attempts, obfuscation, or persistence mechanisms.
Audit Metadata