devtools-audit
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs the agent to review environment variables and shell setups. These locations are frequently used to store sensitive information like API keys, access tokens, and private configuration details, posing an exposure risk.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes data from the local system environment without defining boundary markers or sanitization.
- Ingestion points: Environment variables, shell configuration files, and PATH settings.
- Boundary markers: The instructions do not provide delimiters to separate system data from agent instructions.
- Capability inventory: The skill requires the agent to read system-level environment and configuration files.
- Sanitization: No validation or sanitization instructions are included for the data retrieved during the audit.
- [NO_CODE]: The skill consists entirely of natural language instructions in Markdown format and does not include any executable scripts or code.
Audit Metadata