iam-role-generator
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (HIGH): The skill requests Bash(aws:*) permissions in SKILL.md, allowing arbitrary AWS CLI command execution. This level of access is excessive for a role generator and lacks proper containment or restriction to specific AWS IAM subcommands.
- [PROMPT_INJECTION] (HIGH): High susceptibility to Indirect Prompt Injection (Category 8). The skill processes user-provided role requirements but lacks boundary markers or sanitization, potentially allowing attackers to influence AWS environment state. • Ingestion points: User requests via triggers in SKILL.md. • Boundary markers: Absent. • Capability inventory: Bash(aws:*), Read, Write, Edit. • Sanitization: Absent.
Recommendations
- AI detected serious security threats
Audit Metadata