earth-system-science-data
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of informational text and markdown formatting. It does not include any executable scripts, binary files, or system commands.
- [SAFE]: No evidence of obfuscation, Base64 encoding, or hidden characters was found in the skill metadata or body.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface by instructing the agent to ingest and process data from external and local sources.
- Ingestion points: The skill instructs the agent to read local files (
../../resources/source-basis.mdand../../resources/official-source-map.md) and perform live web searches for "Earth System Science Data author guidelines." - Boundary markers: The instructions lack explicit delimiters or warnings to ignore potentially malicious instructions embedded in the retrieved web content or local resources.
- Capability inventory: The skill itself does not define or request dangerous capabilities such as file-system writes, network exfiltration, or subprocess execution.
- Sanitization: No sanitization or validation logic is provided to filter content retrieved from the external sources.
Audit Metadata