pp-exchangerate-api

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install its core CLI binary via npx and go install from vendor-controlled repositories.
  • Evidence (SKILL.md): npx -y @mvanhorn/printing-press-library install exchangerate-api --cli-only and go install github.com/mvanhorn/printing-press-library/library/payments/exchangerate-api/cmd/exchangerate-api-pp-cli@latest.
  • [COMMAND_EXECUTION]: The skill utilizes the Read Bash tool to execute the exchangerate-api-pp-cli tool for fetching data and performing conversions.
  • Evidence (SKILL.md): exchangerate-api-pp-cli <command> [subcommand] [args] --agent.
  • [DATA_EXFILTRATION]: The CLI includes a --deliver feature that allows for routing command output to local file paths or external webhook URLs.
  • Evidence (SKILL.md): Support for webhook:<url> and file:<path> sinks in the output delivery configuration.
  • [PROMPT_INJECTION]: The skill takes user input from queries to determine which CLI commands to execute, presenting a potential surface for indirect prompt injection if malicious instructions are embedded in the data being processed.
  • Ingestion points: User queries for exchange rates, currency codes, or conversion amounts which are passed to the CLI as arguments.
  • Boundary markers: No specific delimiters or safety warnings are implemented in the shell command templates.
  • Capability inventory: The skill has the ability to write to the file system, make network requests to arbitrary URLs via webhooks, and execute shell commands via Read Bash.
  • Sanitization: The skill does not describe specific sanitization or filtering logic for user-provided arguments before they are interpolated into the shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 05:33 AM
Security Audit — agent-trust-hub — pp-exchangerate-api