The Agent Skills Directory

[SAFE]: The skill is a procedural guide for research methodology. It does not contain any malicious code, obfuscation, or unauthorized access attempts. All instructions are consistent with the stated purpose of improving search results quality.\n- [PROMPT_INJECTION]: The skill instructs the agent to fetch full content from the web, which creates a surface for indirect prompt injection. Evidence Chain: 1. Ingestion points: Web pages fetched via web_fetch as part of the Phase 2 and Phase 3 research methodology. 2. Boundary markers: No specific delimiters or instructions to disregard potential commands within fetched content are provided in the skill instructions. 3. Capability inventory: Relies on search and web_fetch for information retrieval. 4. Sanitization: No sanitization or validation of the fetched external content is described.

deep-research