analyst-ratings-tracker

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the external SentiSense API, which includes free-text fields like attributionNote and insightText. These fields could potentially contain instructions that influence the agent's output.
  • Ingestion points: Multiple API endpoints under https://app.sentisense.ai/api/v1/ and v2/ accessed via curl or the sentisense CLI.
  • Boundary markers: Includes specific "What this data actually is (read before interpreting)" guidelines to help the agent contextually understand the data.
  • Capability inventory: The skill performs network GET requests to fetch financial data and sentiment metrics; it does not perform write operations or trade execution.
  • Sanitization: No explicit mention of sanitizing or escaping the text returned from the API insights before processing.
  • [EXTERNAL_DOWNLOADS]: The skill instructions promote the use of the sentisense package via a package runner to execute vendor-provided logic.
  • Evidence: Mentions npx -y sentisense@0.52.0 for various data retrieval workflows throughout the documentation.
  • Context: This targets the official package for the SentiSense service on the NPM registry, providing a version-pinned CLI tool for interacting with their API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 04:26 AM
Security Audit — agent-trust-hub — analyst-ratings-tracker