greptile
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official npm registry. This is a vendor-owned resource used for managing integrations.
- [COMMAND_EXECUTION]: The instructions involve executing shell commands via the membrane CLI to manage connections and interact with the Greptile API. These operations are aligned with the skill's stated purpose.
- [DATA_EXFILTRATION]: Credential management is handled through a secure login flow (membrane login) rather than hardcoding secrets, which is a recommended security practice.
- [PROMPT_INJECTION]: The skill processes data from external repositories via Greptile, which presents an inherent surface for indirect prompt injection. • Ingestion points: Data returned from action results or proxy requests in SKILL.md. • Boundary markers: Absent in the documented examples. • Capability inventory: File system access and network operations via the Membrane CLI. • Sanitization: Relies on the agent's internal safety filters and the platform's proxy logic.
Audit Metadata