fittings-hts-search

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads a client script from https://fittings.sh/skill/call.mjs. This resource belongs to the skill's author domain and is used to facilitate API communication.
  • [REMOTE_CODE_EXECUTION]: The skill instructs the agent to execute the downloaded call.mjs script using node. This script handles the signing of payment authorizations and the communication with the HTS search endpoint.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (curl and node) to download the client and perform searches. It also requires setting an environment variable (FITTINGS_PRIVATE_KEY) for paid operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the query parameter, which is then interpolated into a shell command.
  • Ingestion points: The query argument in the search command, taken from user product descriptions.
  • Boundary markers: The provided example uses double quotes to delimit the query string.
  • Capability inventory: The skill can perform network requests (curl), execute local scripts (node), and access environment variables.
  • Sanitization: Validation and escaping of the query input are handled by the external call.mjs script rather than the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 10:32 PM