The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and scrape content from external academic and research websites which may contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The obscura fetch and obscura scrape commands, along with helper scripts, ingest arbitrary data from URLs provided at runtime.
Boundary markers: The instructions do not define boundary markers or 'ignore' instructions for the data being fetched.
Capability inventory: The skill has the ability to execute a local binary, perform network requests, and execute JavaScript within a browser environment.
Sanitization: There is no evidence of sanitization or filtering of the external web content before it is processed by the agent.
[DYNAMIC_EXECUTION]: The browser tool supports an --eval flag that allows the agent to execute arbitrary JavaScript code within the context of the fetched page to extract metadata or interact with the DOM.
[COMMAND_EXECUTION]: The skill relies on and executes a local binary located at ~/tools/obscura/obscura. It also uses shell scripts (scripts/obscura_serve.sh, scripts/test_obscura.sh) to manage the CDP server and perform integrity checks, including SHA-256 checksum verification.

obscura