robot-framework-py
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [Indirect Prompt Injection] (HIGH): The skill creates a surface where untrusted data from API responses can influence high-privilege keywords. 1. Ingestion points: API responses via RequestsLibrary keywords in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: OperatingSystem library and custom Python keyword generation. 4. Sanitization: No instructions provided for escaping external content.
- [Unverifiable Dependencies] (MEDIUM): Recommends installation of robotframework-requests which is not from a specifically trusted source.
- [Command Execution] (MEDIUM): Explicitly enables the OperatingSystem library for host environment and file system interaction.
- [Dynamic Execution] (MEDIUM): Facilitates the generation and execution of arbitrary Python keyword libraries at runtime.
Recommendations
- AI detected serious security threats
Audit Metadata