The Agent Skills Directory

[SAFE]: No obfuscation techniques such as Base64 encoding, zero-width characters, or homoglyphs were detected in the skill files or metadata.- [SAFE]: The skill does not attempt to access sensitive files (e.g., .ssh, .env) or hardcode credentials. It reads only from the local references directory.- [SAFE]: No remote code execution or suspicious package dependencies were identified. The skill relies on standard sub-agent calls and local file operations.- [SAFE]: No prompt injection or behavior override patterns were found. The instructions for the sub-agents are clearly structured and focused on the intended analysis task.- [SAFE]: While the skill processes user-provided headlines, it uses structured boundaries in its prompts to sub-agents. Analysis of the capability surface shows that inputs are used for information processing within a confined investment analysis context.

scenario-analyzer