research-paper-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external research papers which could potentially contain adversarial text or instructions designed to manipulate the agent's critique.
- Ingestion points: Research paper text provided to the agent for review (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the analyzed content.
- Capability inventory: The skill does not use tools for file modification, network access, or command execution, limiting the potential impact of an injection.
- Sanitization: No sanitization or filtering of the input text is defined in the prompt instructions.
Audit Metadata