cli-cost-usage

Warn

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the user to install a third-party global package 'omniroute' via 'npm install -g'. This executes code from an external source that is not part of the provided trusted vendors list.\n- [EXTERNAL_DOWNLOADS]: The installation process fetches the 'omniroute' package and its entire dependency tree from the public NPM registry.\n- [CREDENTIALS_UNSAFE]: Multiple subcommands (e.g., 'cost', 'usage logs', 'usage utilization') include an '--api-key' flag. Passing sensitive credentials as command-line arguments is a security risk as they can be exposed in shell history, process listings, or log files.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its log-monitoring features.\n
  • Ingestion points: The 'usage logs' and 'usage history' commands retrieve data from external AI provider logs, which could contain malicious instructions embedded in previous model outputs or inputs (SKILL.md).\n
  • Boundary markers: No delimiters or instructions are provided to the agent to distinguish between the retrieved data and its own system instructions.\n
  • Capability inventory: The agent has the ability to execute shell commands and manage budget/pricing configurations via the 'omniroute' tool.\n
  • Sanitization: There is no evidence of sanitization or validation of the log content before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 15, 2026, 01:51 AM
Security Audit — agent-trust-hub — cli-cost-usage