famou-artifact-generator
Warn
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute generated Python scripts locally using the command 'python evaluator.py <path_to_init.py>'. This execution of dynamically generated code based on environment data is a security risk.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests project files (README, data files, configurations) to generate task definitions and executable code.
- Ingestion points: Project files accessed in Phase 1, Step 1.
- Boundary markers: Not used to delimit external content.
- Capability inventory: File system write access and shell command execution.
- Sanitization: No content validation or sanitization is applied.
Audit Metadata