rlm
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process and summarize large volumes of untrusted external data, including codebases, logs, and data dumps. This creates an attack surface where adversarial instructions embedded within the analyzed content could attempt to manipulate the agent's reasoning or the resulting summaries.
Audit Metadata