Continuous red teaming platform for testing and securing LLM agents AI-generated from public sourcesThe starting point for every profile: auto-generated by 0-Doubt from public vendor materials, and not yet confirmed by the vendor or an independent analyst. Nothing here is hidden or overstated — it simply has not been reviewed yet.Where every profile starts, before the vendor or an analyst has reviewed it. A higher label means a more independent source — not a better product.How trust works →
Tools & products
Read by an AI model from giskard.ai’s own pages. What the vendor says it does, not independently verified.
Showing the 12 closest of 126 — see all.
1 of 5 independent trust signals established
Giskard has one dimension with established evidence. The rest have not been confirmed yet.
Not yet established: Independently verified · Behaviour under stress · Disclosure posture · Momentum
Has anyone other than the vendor confirmed this?
Nothing here has been confirmed by an independent third party yet.
Is this a real, durable business?
How long this vendor has been operating, and who stands behind them.
Security headers (3/5) — checked 10/18/2026
Infrastructure & transparency signals
Likely-exploited estimates here rest on a median of 2 EPSS observations per CVE — too little history to read as a trend yet. It deepens daily as scores are collected.
Giskard is an open-source testing framework for AI models. In versions prior to 1.0.2b1, the ConformityCheck class rendered the rule parameter through Jinja2's default Template() constructor, silently…
Giskard is an open-source testing framework for AI models. In versions prior to 1.0.2b1, the RegexMatching check passes a user-supplied regular expression pattern directly to Python's re.search() with…
Not a quality rating or endorsement — a measure of how much verified, disclosed data we actually have about this vendor. A low score usually means "we don't have much verified information yet," not "this is a bad vendor." Never used to sort or rank vendor lists.
The platform admin controls the formula's weights.
Product information on this page is auto-generated by 0-Doubt from public sources and not yet confirmed by the vendor or an independent analyst, unless an item is individually labelled otherwise. How trust works →
What do they do when something goes wrong?
What their public record shows about handling vulnerabilities and outages.
Do they tell you the awkward things unprompted?
How much this vendor volunteers before you have to ask.
Are they still shipping, or coasting?
Whether this vendor is visibly still building.
Nothing checked here yet — this is not a mark against Giskard.
Giskard is an evaluation and testing framework for AI systems. A Remote Code Execution (ReDoS) vulnerability was discovered in Giskard component by the GitHub S…
Giskard is an open-source Python library for testing and evaluating agentic systems. Prior to versions 0.3.4 and 1.0.2b1, ChatWorkflow.chat(message) passes its …
Giskard is an open-source testing framework for AI models. In versions prior to 1.0.2b1, the ConformityCheck class rendered the rule parameter through Jinja2's …
Giskard is an open-source testing framework for AI models. In versions prior to 1.0.2b1, the RegexMatching check passes a user-supplied regular expression patte…
Giskard is an open-source Python library for testing and evaluating agentic systems. Prior to versions 0.3.4 and 1.0.2b1, ChatWorkflow.chat(message) passes its string argument directly as a Jinja2 tem…
Giskard is an evaluation and testing framework for AI systems. A Remote Code Execution (ReDoS) vulnerability was discovered in Giskard component by the GitHub Security Lab team. When processing datase…