open-policy-agent
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the npm registry to interact with the service. - [COMMAND_EXECUTION]: The skill relies on executing the
membranecommand-line utility for authentication, managing connections, and performing API requests. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source (Open Policy Agent) which may contain untrusted content.
- Ingestion points: Data retrieved via
membrane action runandmembrane requestare ingested into the agent's context (SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill instructions.
- Capability inventory: The skill allows executing CLI commands and performing network requests through a proxy, providing a functional path for injected instructions.
- Sanitization: No explicit sanitization or validation of the data returned from the policy engine is described.
Audit Metadata