Coursework for 'Transformers, LLMs, RAG and Agents: From Theory to Production' (BSC x UPC): RAG applications, hand-built agent loops, and token-cost experiments measured on a local stack
- capability exposure inferred + 35
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 1m ago · see ecosystem CVEs →
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit e64da5b · analyzer v28 · 1d ago
skills & prompt files 4
- agent-rules carco5-ludo-engsoft-e64da5b/week-03/demos/04-minimal-cli-agent/agent.md
- skill carco5-ludo-engsoft-e64da5b/week-03/demos/04-minimal-cli-agent/skills/word-report/skill.md
- agent-rules carco5-ludo-engsoft-e64da5b/week-03/token-bill/part2-two-roads/road-cli/agent.md
- skill carco5-ludo-engsoft-e64da5b/week-03/token-bill/part2-two-roads/road-cli/skills/forum-cli/skill.md
[](https://mcpobservatory.com/servers/github:carco5/ludo-engsoft/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of carco5.