capgo-cloud
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends using
npx @capgo/cli@latest, which involves downloading the official CLI package from the public registry at runtime. As this is a vendor-owned package, it is a standard part of the tool's functionality. - [COMMAND_EXECUTION]: The instructions include shell commands for configuring MCP servers (
claude mcp add) and executing the CLI (npx). These commands are intended to facilitate the connection between the AI agent and the Capgo cloud services. - [INDIRECT_PROMPT_INJECTION]: The skill processes user requests to route them to specific sub-skills, creating a potential surface for indirect injection via manipulated project requirements.
- Ingestion points: User requests described in SKILL.md.
- Boundary markers: None explicitly defined within the routing logic.
- Capability inventory: Tool routing, MCP server registration, and CLI execution commands.
- Sanitization: Not explicitly present; the skill relies on the underlying platform's handling of specific routed skills.
Audit Metadata