The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected in this skill.
[EXTERNAL_DOWNLOADS]: The skill connects to the vendor's official API at xquik.com to retrieve hashtag data. This is expected behavior for a social media monitoring tool.
[PROMPT_INJECTION]: The skill ingests untrusted third-party data from X (Twitter). This represents a surface for indirect prompt injection.
Ingestion points: Untrusted content enters the agent context through the search and monitoring endpoints (GET /x/tweets/search, POST /monitors) described in SKILL.md.
Boundary markers: The skill includes a dedicated 'Security' section that explicitly warns the agent to treat tweet text as untrusted content.
Capability inventory: The skill's configuration (codeExecution: none, executionModel: api-only) minimizes the risk that an injection could lead to system-level exploitation.
Sanitization: The skill relies on natural language instructions to guide the agent in ignoring embedded malicious commands.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by recommending the use of environment variables (XQUIK_API_KEY) for authentication rather than hardcoding secrets.

track-hashtags