log-focus-debug
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill provides instructions for the agent to execute
rg(ripgrep) to find temporary focus tokens andyarn eslintto verify code changes. These are standard development tools used for their intended purposes. - [DATA_EXPOSURE] (LOW): The skill guides the agent to modify
.envfiles for log configuration. Although.envfiles often contain secrets, the specific variables targeted (e.g.,DP_LOG_LEVEL,DP_LOG_FOCUS_TOKEN) are for debugging and do not involve credential exfiltration. - [PROMPT_INJECTION] (LOW): The skill exposes an indirect prompt injection surface (Category 8) because the agent is instructed to read and process source code and log outputs. These external data sources could potentially contain malicious instructions intended to manipulate the agent's behavior.
Audit Metadata