alphaear-signal-tracker

Track finance investment signal evolution and update logic based on new finance market information. Use when monitoring finance signals and determining if th...

Security Scan

The skill's stated purpose (finance signal tracking) generally matches its code and prompts, but there are transparency and scope mismatches that warrant caution (network scraping, local DB writes, and implicit config/file access not declared in the manifest).

Purpose & Capability

Name/description match what the package does: the code and prompts implement research, signal parsing, tracking, and reporting for financial signals. Declared dependencies ('agno' and sqlite3) align with the toolkit and DB usage seen in scripts/tools/toolkits.py and scripts/fin_agent.py.

Instruction Scope

Prompts and SKILL.md instruct agents to fetch web content, call tool methods like search_ticker/get_stock_price, and run multi-step agentic workflows. The prompts require: (a) fetching arbitrary URLs and webpage content (scripts/tools/toolkits.py -> fetch_news_content), (b) updating a local database (enrich_news_content executes SQL UPDATE on daily_news), and (c) strict requirements to call tools 'for EVERY mentioned company'. These actions go beyond pure 'analysis' and involve network I/O and modifications to local storage; the SKILL.md does not explicitly call out these side-effects in a security-transparent way.

Install Mechanism

No external install/downloads are specified (no install spec). All code is packaged with the skill, so there is no high-risk remote fetch during installation. This reduces supply-chain concerns, though running the included code will perform network I/O at runtime.

Credentials

The skill declares no required environment variables or config paths, but several code paths access local files and config directories (e.g., scripts/schema/isq_template.py -> load_templates_from_config reads config/isq_templates or a given config path) and a DatabaseManager (scripts/fin_agent.py, scripts/tools/toolkits.py) is used for lookups and writes. The absence of declared config/DB paths or any credential requirements reduces transparency: the skill may attempt to read local config files or create/update a local sqlite DB without notifying the user or declaring where data will be stored.

Persistence & Privilege

The skill does not request 'always: true' and does not appear to modify other skills or system-wide agent settings. However it does perform persistent actions within its own domain (reading template JSON from config paths and writing to a local DB table daily_news). That behavior is expected for a tracker/reporting tool but should be reviewed before running with sensitive data or in privileged environments.

What to consider before installing

This skill implements an agentic financial research and signal-tracking pipeline that will: fetch web pages and news, call external data/tool skills (alphaear-search, alphaear-stock), and read/write a local sqlite database. Before installing/running: 1) Review scripts/utils/database_manager.py and scripts/utils/news_tools.py to confirm where the DB files live and what data is written (the toolkits perform SQL UPDATEs). 2) Expect runtime network requests to arbitrary URLs (fetch_news_content) and ensure the execution environment is safe and sandboxed. 3) Note the skill can load JSON templates from a config directory (scripts/schema/isq_template.py -> load_templates_from_config) even though no config paths or env vars are declared—validate those file-read behaviors. 4) If you need to limit risk, run it in an isolated environment, disable autonomous invocation if you do not want the agent to call these tools automatically, and do not provide sensitive credentials or system-level file access. If you want a cleaner guarantee, request that the author explicitly declare DB paths, any external API keys the code expects, and document all persistent writes the skill performs.

AlphaEar Signal Tracker Skill

Overview

This skill provides logic to track and update investment signals. It assesses how new market information impacts existing signals (Strengthened, Weakened, Falsified, or Unchanged).

Capabilities

1. Track Signal Evolution

1. Track Signal Evolution (Agentic Workflow)

YOU (the Agent) are the Tracker. Use the prompts in references/PROMPTS.md.

Workflow:

1. Research: Use FinResearcher Prompt to gather facts/price for a signal.
2. Analyze: Use FinAnalyst Prompt to generate the initial InvestmentSignal.
3. Track: For existing signals, use Signal Tracking Prompt to assess evolution (Strengthened/Weakened/Falsified) based on new info.

Tools:

• Use alphaear-search and alphaear-stock skills to gather the necessary data.
• Use scripts/fin_agent.py helper _sanitize_signal_output if needing to clean JSON.

Key Logic:

• Input: Existing Signal State + New Information (News/Price).
• Process:
  1. Compare new info with signal thesis.
  2. Determine impact direction (Positive/Negative/Neutral).
  3. Update confidence and intensity.
• Output: Updated Signal.

Example Usage (Conceptual):

# This skill is currently a pattern extracted from FinAgent.
# In a future refactor, it should be a standalone utility class.
# For now, refer to `scripts/fin_agent.py`'s `track_signal` method implementation.

Dependencies

• agno (Agent framework)
• sqlite3 (built-in)

Ensure DatabaseManager is initialized correctly.