Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed stock-research skill with no executable or persistence behavior, but it can produce actionable trade-style outputs that users should treat only as research.
Install only if you want an educational stock-research workflow that may generate buy/sell/hold-style analysis, price targets, stop-losses, and position-sizing examples. Do not treat its outputs as personalized financial advice or let them drive real trades without independent review by a qualified professional.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
## Thesis & Exit Criteria
**Investment Thesis**:
[Clear statement of why we're making this trade]
**Exit Triggers**:
- [ ] Target price reached
The manifest advertises very broad trigger phrases such as stock analysis, trading decision, investment analysis, and buy/sell/hold recommendation, which can cause the skill to activate on common finance-related requests without clear scoping. In a multi-skill environment, this increases the chance of inappropriate routing into a workflow that produces high-risk financial content and execution-style outputs.
Although the file later says not to provide financial advice, the skill prominently defines actionable recommendation outputs including BUY/SELL/HOLD, trade orders, stop-losses, targets, and execution plans. That mismatch makes the safety warning ineffective in practice and can steer the agent into generating personalized or execution-oriented financial guidance despite the nominal disclaimer.