rk-method
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external project files such as scientific notes and documentation to help researchers generate method plans.
- Ingestion points: Scientific notes,
AGENTS.md, and other project files in the working directory or specified in user requests. - Boundary markers: The skill does not define specific delimiters or explicit instructions to the agent to disregard potential instructions embedded within the research notes it reads.
- Capability inventory: The skill performs file writing (e.g., filling
method-plan.md, creating manuscript drafts or figures). It does not have access to network tools, shell execution, or dynamic code evaluation. - Sanitization: No specific sanitization or filtering of external content is mentioned.
- [SAFE]: The skill includes explicit safety constraints, such as prohibiting the authorization of financial transactions or the submission of external jobs. It focuses entirely on procedural research planning without incorporating executable code or remote dependencies.
Audit Metadata