famou-artifact-generator
Warn
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run a shell command (
python evaluator.py <path_to_init.py>) to validate generated code artifacts. - [REMOTE_CODE_EXECUTION]: The skill involves dynamic code execution by generating Python files (
init.py,evaluator.py) and immediately executing them. This is a risk as the generated logic depends on external project data and user input which could be used to inject malicious code. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes untrusted data from the project environment (README, data files, code scripts) to automate the creation of task specifications.
- Ingestion points: Project files including README, configuration files, and data samples in Step 1.
- Boundary markers: None specified; external content is used directly to determine task logic.
- Capability inventory: Includes file system writes and subprocess execution.
- Sanitization: No validation or sanitization of the contents of the read files is performed before they influence the implementation phase.
Audit Metadata