codesee
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
@membranehq/clipackage from the NPM registry. This is a standard installation for the vendor's command-line tool used to facilitate the integration. - [COMMAND_EXECUTION]: The skill utilizes the
membraneCLI to perform operations such as logging in, creating connections, and executing API actions. These commands are necessary for the primary function of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external CodeSee API endpoints, which represents a potential attack surface.
- Ingestion points: Data returned from CodeSee actions and proxy requests via the
membraneCLI (SKILL.md). - Boundary markers: None. The skill does not implement specific delimiters to separate user/developer instructions from data retrieved from the API.
- Capability inventory: The skill can execute shell commands (
membraneCLI) and perform network operations (SKILL.md). - Sanitization: No validation or sanitization of the remote API output is described before the data is processed by the agent.
Audit Metadata