The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The skill instructs the agent to use administrative privileges via the sudo command to start the Tor service (sudo service tor start).
[COMMAND_EXECUTION]: The skill relies on shell command execution to run the maigret CLI tool and uses shell scripting loops to process multiple usernames variant.
[INDIRECT_PROMPT_INJECTION]: The skill has a significant attack surface for indirect prompt injection by ingesting untrusted data from thousands of external websites. * Ingestion points: The tool extracts profile data such as names, bios, and locations from up to 5,900 external sites. * Boundary markers: There are no explicit instructions or markers to delimit external content or warn the agent to ignore embedded instructions. * Capability inventory: The skill has the capability to execute shell commands via the CLI tool. * Sanitization: No sanitization or filtering of the ingested external content is described.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the maigret Python package from the public PyPI registry.

maigret