The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes unstructured text from external websites through its search functionality.
Ingestion points: Web content is ingested through the /tsearch/search API call in scripts/tsearch_web_search.py.
Boundary markers: There are no explicit instructions or delimiters defined to isolate external web content from the agent's system instructions.
Capability inventory: The skill has the ability to write files to the local project directory and perform network requests to vendor APIs.
Sanitization: The skill does not perform sanitization or filtering on the retrieved web content before passing it to the agent.
[COMMAND_EXECUTION]: The skill executes local Python scripts (tsearch_web_search.py and onboarding.py) to facilitate its core functions. These scripts manage API communication, handle user authentication workflows (including QR code generation for payments), and log search results to the local filesystem.
[SAFE]: The skill communicates with author-owned API endpoints (linkfox.com, tool-gateway.linkfox.com, agent-api.linkfox.com) for its intended search and authentication features. All network operations and file system activities are consistent with the skill's stated purpose of providing a web search engine and account management interface.

linkfox-tsearch-search