The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any code, scripts, or tool configurations that could execute commands or perform network operations.
[PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection as it instructs the agent to analyze untrusted external inputs like HTTP headers, cookies, and API payloads. However, this is inherent to the skill's purpose for security research and no malicious override patterns were detected. Ingestion points: Data entering the context from URLs, query parameters, JSON, and HTTP headers as described in the 'Operating Model' section of SKILL.md. Boundary markers: None identified. Capability inventory: No capabilities or tools are defined or called by this skill file. Sanitization: No validation or sanitization of external data is specified.

hack