cargo-quickstart

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a sequence of shell commands including npm, cargo-ai, curl, and jq to perform installation, authentication, and data processing.
  • [EXTERNAL_DOWNLOADS]: The skill installs the @cargo-ai/cli package from the official NPM registry and fetches search results via curl from signed URLs generated by the vendor's orchestration tool. These resources originate from the skill's authoring organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts untrusted user input to define a buyer persona which is then used to construct a command line for the cargo-ai CLI. • Ingestion points: User input provided in response to the persona question in SKILL.md. • Boundary markers: None present; the input is placed directly into a command template. • Capability inventory: The skill has access to shell execution and network downloads via the CLI and curl. • Sanitization: No explicit sanitization or validation of the persona string is defined before its inclusion in the shell command.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:53 AM
Security Audit — agent-trust-hub — cargo-quickstart