ru-score
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted text provided by the user for scoring analysis.
- Ingestion points: Untrusted text enters the agent context through the $ARGUMENTS variable or by reading recent conversation history.
- Boundary markers: The skill instructions do not specify the use of delimiters (such as triple backticks or XML tags) or explicit instructions for the agent to ignore commands embedded within the text being analyzed.
- Capability inventory: The skill utilizes Read, Grep, and Glob tools for accessing local reference files.
- Sanitization: There is no process described for sanitizing or filtering user input to prevent it from influencing the agent's behavior during the scoring process.
Audit Metadata