stock-rumors-aisa

Scan M&A, insider, analyst, social, and regulatory rumor signals through AISA. Use when: the user asks about early market signals, rumors, insider activity,...

Security Scan

The skill and included script are internally consistent with their stated purpose (scanning rumor signals via the AISA API) and request only a single, relevant API key; no obvious mismatches or unexpected privileges were found.

Purpose & Capability

Name/description, required binary (python3), and required env var (AISA_API_KEY) match the included Python script which calls an AISA-compatible API endpoint. There are no unrelated credentials, binaries, or config paths requested.

Instruction Scope

SKILL.md instructs running the bundled Python client which in turn asks an AISA model to 'fetch live data' and scan news/filings/social signals. The script itself does not independently call news/EDGAR/options APIs — it relies on the AISA model backend (via the OpenAI-compatible client) to provide those signals. This is a reasonable design but means the skill's ability to actually fetch live external records depends on the AISA service rather than local connectors; verify you trust that service and understand what data it returns.

Install Mechanism

There is no install spec (instruction-only with a bundled script). The script imports the openai Python package (commented as a dependency) but the skill does not provide an automated installation step. Users must have python3 and the appropriate Python package(s) installed; ensure you install dependencies from trusted sources.

Credentials

The skill requires a single primary credential (AISA_API_KEY) and optionally reads AISA_BASE_URL and AISA_MODEL environment variables. These are proportionate to a service-backed rumor scanner. No unrelated SECRET/TOKEN/PASSWORD env vars are requested.

Persistence & Privilege

The skill is not marked always:true, does not request persistent system-level changes, and does not modify other skills or system-wide config. Autonomous invocation is enabled (default) but that is expected for skills.

Assessment

Before installing or running: 1) Confirm the AISA provider (AISA_BASE_URL default is https://api.aisa.one/v1) is a trusted service and that the API key you supply has appropriate scope/quotas — avoid using wide-ranging production credentials. 2) Be aware the script relies on the remote model/backend to 'fetch' live news and filings; the model may hallucinate or provide summaries without linking to primary sources, so verify any signals against original filings/news. 3) The repository does not include an automated dependency install step; install required Python packages (e.g., openai) from official sources and review them. 4) Handle rumors carefully (legal/regulatory and market risks) and do not feed local secrets or unrelated credentials to the skill. If you need stronger assurance, request documentation or an SLA from the AISA provider showing how their model obtains and verifies live financial data.

Rumor Scanner

When to Use

• Scan M&A, insider, analyst, social, and regulatory rumor signals through AISA. Use when: the user asks about early market signals, rumors, insider activity, analyst changes, or takeover chatter.

When NOT to Use

• Do not use this skill for browser-cookie extraction, passwords, Keychain access, or other local sensitive credential access.
• Prefer a different skill when the user request is outside this skill's domain.

Capabilities

• Rank rumor-like signals by likely impact across several signal categories.

Quick Start

export AISA_API_KEY="your-key"

Primary Runtime

Use the bundled Python client as the canonical ClawHub runtime path:

python3 scripts/rumor_scanner.py

Example Queries

• Scan for the strongest takeover or insider signals this week.

Notes

• Rumors are unconfirmed and should be independently verified.