fittings-fx-convert

Warn

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: MEDIUMCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a functional JavaScript client directly from the vendor's domain (https://fittings.sh/skill/call.mjs) to handle API communication and payments.
  • [REMOTE_CODE_EXECUTION]: Instructions direct the user to execute the downloaded script using the Node.js runtime (node call.mjs), which constitutes execution of remote code.
  • [CREDENTIALS_UNSAFE]: The documentation instructs users to export a blockchain private key (FITTINGS_PRIVATE_KEY) as a plaintext environment variable. The skill explicitly notes that the key remains in plaintext during execution, which poses a significant risk of credential exposure if the environment is compromised.
  • [COMMAND_EXECUTION]: The skill relies on shell commands (curl, node, export, jq) for its installation and primary functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API which could potentially be used to influence agent behavior, as the agent has the capability to write files and execute shell commands.
  • Ingestion points: API responses from https://fittings.sh/v1/fx/convert.
  • Boundary markers: None provided in the instructions.
  • Capability inventory: File system writes (curl -sO), shell command execution (node).
  • Sanitization: No explicit sanitization or validation of the API's returned data is mentioned before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 17, 2026, 10:32 PM