The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documents the installation of the robotframework-requests library and specialized authentication modules including requests-ntlm and requests-aws4auth from official package registries.\n- [COMMAND_EXECUTION]: The documentation includes standard shell commands for package installation using pip and process verification using curl, as seen in SKILL.md and references/troubleshooting.md.\n- [PRIVILEGE_ESCALATION]: The troubleshooting guide in references/troubleshooting.md suggests the use of sudo for updating system-level CA certificates on Linux environments.\n- [INDIRECT_PROMPT_INJECTION]: The skill provides the ability to ingest data from external REST APIs, establishing an attack surface for untrusted content.\n
Ingestion points: External data enters the agent context via API response bodies and headers using keywords like ${response.json()} and ${response.text}.\n
Boundary markers: No explicit markers or delimiters are used to isolate ingested API data from the agent's internal instructions.\n
Capability inventory: The skill possesses capabilities for network operations (HTTP methods), file system writes (e.g., Create Binary File in assets/examples/file-upload.robot), and arbitrary Python evaluation through the Evaluate keyword.\n
Sanitization: The provided examples focus on functional validation and do not demonstrate escaping or sanitization of external content before processing.

requests