paper-research
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill imports its core execution logic from an external source:
literature-engine/skills/literature-research/SKILL.md. This creates a dependency on an external repository that is not part of the trusted vendor list.- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. - Ingestion points: The skill is designed for "raw text extraction" and "full-depth paper reading" from academic literature (SKILL.md).
- Boundary markers: There are no defined delimiters or instructions provided to separate the untrusted content of the papers from the agent's internal instructions.
- Capability inventory: Extracted data including equations, hyperparameters, and implementation details are processed and returned to the agent's context.
- Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the content extracted from external papers.
Audit Metadata