capgo-organization-management
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use
npxto download the@capgo/clipackage, which is the official tool provided by the vendor. - [REMOTE_CODE_EXECUTION]: The use of
npx @capgo/cli@latestallows for the remote execution of code from the NPM registry, specifically the vendor's CLI tool. - [COMMAND_EXECUTION]: The skill involves running administrative CLI commands to manage organizations, members, and security settings.
- [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection when processing output from commands like
organization listor member inspection. * Ingestion points: Output from CLI commands (SKILL.md). * Boundary markers: No specific delimiters or safety instructions are defined to separate data from commands. * Capability inventory: The skill utilizes CLI command execution via subprocesses. * Sanitization: There is no evidence of sanitization or validation of the CLI output before it is processed by the agent.
Audit Metadata