sparebank1-shared

Warn

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install an external binary using cargo install sparebank1-cli. This downloads and executes unverified third-party code from a public registry.
  • [COMMAND_EXECUTION]: The skill's primary function is to execute the sb1 CLI binary to perform actions like authentication, account listing, and transaction retrieval.
  • [CREDENTIALS_UNSAFE]: The skill describes a configuration option (SB1_STORE=file) that stores authentication tokens in plaintext within the user's home directory (~/.config/sparebank1-cli/*.json). While documented as opt-in for headless use, this increases the risk of credential exposure if the local system is compromised.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external API.
  • Ingestion points: Account names and transaction descriptions retrieved from the SpareBank 1 API (e.g., via sb1 transactions).
  • Boundary markers: No specific delimiters or instructions to ignore embedded content in API responses are defined.
  • Capability inventory: The agent can execute shell commands via the sb1 CLI and access the local file system for configuration.
  • Sanitization: There is no evidence of sanitization or escaping of the data fetched from the bank API before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 28, 2026, 01:58 PM
Security Audit — agent-trust-hub — sparebank1-shared