Agent classes / Security review agent / Programmable LLM input/output guardrails

Programmable LLM input/output guardrails for a security review agent

Updated 2026-10-27 (newest stored date on this page) · score asOf 2026-09-14 (stale)

The class: Reads a change or a trace for secrets, overly broad permissions, and untrusted text copied into a tool prompt. It does not produce an attack.

A findings list with file and line, not a payload
Secrets detected are redacted in the report

Depot Pick: NVIDIA NeMo Guardrails

When not to use it: Need a dedicated prompt-injection API — lakera; only need free category flags — openai-moderation; production hallucination monitoring SaaS — galileo; cheap Llama Guard leaf — groq.

Runner-up: Lakera Guard.

Cheapest matching sourced SKU (usd_per_1k_requests): OpenAI Moderation omni-moderation-latest (moderation endpoint) $0 — source, asOf 2026-10-21. All sourced prices

Failure modes this class and job share (4)

Eval contamination: Keep gold labels out of the agent prompt. Store the harness version beside the score. Do not compare a number across a benchmark revision without saying the revision changed.
Over-refusal: Log refusals separately from successes. Review a sample against the written policy. Do not treat a refusal as a pass, and do not weaken a safety check to raise the pass rate.
Prompt injection: Compare each tool call to the original user task. If the call only makes sense given text that arrived from a fetched page, file, or message, stop and ask. Record which source the instruction came from. This catalog does not store payloads or attack steps.
Weak verification: Success requires an end-state check the agent does not grade for itself: tests, a database diff, or a separate judge that cannot see the gold label.

Free options this class uses (0)

No free row lists this job with a kind this class needs.