The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires three third-party research skills to function, which are fetched from unverified GitHub repositories.
Dependencies include eng0ai/eng0-template-skills@financial-deep-research, ognjengt/founder-skills@competitor-intel, and sickn33/antigravity-awesome-skills@app-store-optimization.
The installation process uses npx skills add, which downloads and executes remote skill content.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of ingesting and synthesizing untrusted data from the web.
Ingestion points: Untrusted data enters the agent context via WebSearch, WebFetch, and curl tool outputs across five specialist agents.
Boundary markers: The provided instructions do not include explicit delimiters or "ignore embedded instructions" warnings for the fetched web content.
Capability inventory: The skill has high capabilities including Bash access, curl for network operations, and the Task tool for spawning sub-agents.
Sanitization: There is no evidence of sanitization or filtering of external content before it is processed by the specialist agents.

deep-dive-research-orchestrator