The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill processes untrusted data from various external sources including Google News RSS and SEC EDGAR. This data could potentially contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Google News RSS, Yahoo Finance, SEC EDGAR, CNN Fear & Greed.
Boundary markers: No specific boundary markers or delimiters for external content are defined in the instructions.
Capability inventory: Execution of local Python scripts via the uv tool, and read/write access to the local filesystem at ~/.clawdbot/.
Sanitization: No explicit sanitization or validation of the fetched external content is described in the documentation.
[Command Execution] (SAFE): The skill utilizes the uv package manager to run local scripts (analyze_stock.py, portfolio.py). This behavior is consistent with the skill's stated purpose of providing an analytical toolset.
[Data Exposure] (SAFE): The skill stores portfolio data in a hidden directory within the user's home folder (~/.clawdbot/skills/stock-analysis/portfolios.json). This is a standard practice for local application data persistence and does not involve accessing sensitive system or credential files.

stock-analysis