sayed/research-pipeline
Produce a rigorous, verified, fully-cited research report on ANY topic by running a disciplined five-stage pipeline: CLARIFY the question, PLAN (an editable research plan), FAN-OUT parallel search subagents, VERIFY every key claim (cross-source + adversarial + cross-model), then SYNTHESIZE a cited report. Use this WHENEVER the user wants real research rather than a quick answer — "research X", "do a deep dive on Y", "write me a report / brief / literature review on Z", "compare A vs B and back it with sources", "what's the state of the art in …", "investigate …", "find evidence for/against …", "give me a market/landscape/competitor analysis", or any question where being wrong is costly and the answer needs citations. Trigger even when the user does not say the word "research" but clearly needs multi-source, fact-checked, cited output. This is the general-topic web-research orchestrator — not the codebase-to-wiki `deep-research` skill. For a fast single-fact lookup, answer directly instead.
75
94%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
High risk: the required FAN-OUT SEARCH stage fetches and READs arbitrary public web pages at runtime (WebFetch) and uses their quoted passages as LLM input for the subsequent VERIFY and SYNTHESIZE stages, so outsider-authored free-text from the web can be incorporated into the model context.
Where we found it
arbitrary public web pages (WebFetch)
content-type · 1 site
The FAN-OUT SEARCH stage explicitly instructs subagents to fetch and read arbitrary public web pages via WebFetch, then use the quoted passages as LLM input for the VERIFY and SYNTHESIZE stages.
references/playbook.md
65
- Open and READ the most relevant sources with WebFetch. NEVER report a claim from a search snippet you
- Audited
- Security analysis