access-policy-designer
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a design and documentation tool. It provides a structured protocol for the AI agent to follow when generating database security policies.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation patterns (e.g., sudo) were found in the skill files.
- [DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive local files (such as SSH keys or environment variables). It only writes documentation to the local
docs/database-report/directory. - [REMOTE_CODE_EXECUTION]: There are no external dependencies, remote scripts, or dynamic code execution patterns (e.g., eval, exec) present.
- [PROMPT_INJECTION]: The instructions focus entirely on its stated purpose of database policy design and do not contain any patterns intended to bypass safety filters or override system instructions.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted user business rules to generate SQL, it has no dangerous capabilities (like network access) that would allow for an exploit chain. It also includes explicit guardrails to warn users about recursive policies or performance issues.
Audit Metadata