monitoring-deployments

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill automatically installs a package (tugboat-cli) from a private GitHub Enterprise instance (git+ssh://git@ghe.spotify.net/warpspeed/tugboat-cli.git). While internal to an organization, this source is not in the trusted whitelist and represents an unverified dependency.
  • COMMAND_EXECUTION (MEDIUM): The skill uses uv tool install and executes several tugboat and gcloud subcommands. Specifically, it instructs the agent to 'Parse log info from tugboat output and run' a gcloud command, which involves dynamic command construction based on external data.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill is vulnerable to indirect injection because it processes untrusted data from deployment outputs.
  • Ingestion points: Data returned from tugboat deployments show and tugboat installations list.
  • Boundary markers: None present; the agent is instructed to parse and use the data directly.
  • Capability inventory: Execution of gcloud logging tail and tugboat CLI commands.
  • Sanitization: No evidence of sanitization or escaping for the parsed log filters or installation IDs before they are interpolated into shell commands.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:39 PM