nature-climate-change
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze research manuscripts, which constitutes untrusted external data.
- Ingestion points: The skill ingests manuscript content in SKILL.md to evaluate journal fit and framing.
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the manuscript input.
- Capability inventory: The skill triggers file read operations for local resources (e.g.,
../../resources/source-basis.md) and instructs the agent to search external websites for live author instructions. - Sanitization: The skill does not specify sanitization or validation logic for the ingested manuscript content.
Audit Metadata