Legal Risk Assessment

Official Anthropic skill for structuring legal risk by severity, likelihood, and escalation needs.

Legal Risk Assessment is an official Anthropic skill from the Legal Productivity Plugin in the public knowledge-work-plugins repository. It helps in-house legal teams record and compare legal risks in contracts, transactions, regulatory questions, potential disputes, and other matters. According to the provider, the skill is a structuring aid rather than legal advice. Qualified legal professionals must review outputs before they influence an approval, negotiation, filing, notification, or another legally significant decision. The skill is therefore best understood as a shared framework for intake, prioritization, documentation, and escalation.

Purpose and method

The core method uses a matrix of severity and likelihood. Severity describes possible financial, operational, reputational, regulatory, and personal consequences if a risk materializes. Likelihood describes how plausible the event is in light of triggers, precedent, current conditions, and available facts. The two assessments produce a risk score that maps to low, medium, high, or critical treatment. According to the provider, this classification is not mathematical truth. It is a consistent language that helps teams compare matters, explain reasoning, and assign responsibility.

Responsible use begins with a clear statement of the matter. Capture the parties, document or event, known facts, open assumptions, relevant timing, and business context. The skill can then organize contributing factors, existing controls, mitigation options, residual risk, monitoring triggers, and next steps. A useful result distinguishes source facts from provisional inferences and identifies questions that require human judgment or additional evidence. This makes the assessment easier to review and less likely to be mistaken for a definitive opinion.

Classification and escalation

Low risks can generally be documented and monitored through ordinary controls. Medium risks usually need a concrete mitigation, an owner, and periodic follow-up. High risks call for senior counsel involvement, a detailed action plan, and potentially specialized external advice, according to the provider. Critical risks should be escalated promptly to the appropriate senior legal and business leaders. Examples of strong escalation triggers include active litigation, a government investigation, possible criminal exposure, a significant data incident, a material contract breach, or a matter that may require board attention.

Organizations must adapt these thresholds to their risk appetite, industry, operating model, and jurisdiction. A result is not safe merely because a number or color was generated. Keep working assumptions separate from legal conclusions. An unusual governing-law clause, an uncapped indemnity, uncertain data processing, or a possible intellectual-property conflict may deserve very different treatment depending on the facts. The skill offers a framework, not a universal materiality threshold or a substitute for jurisdiction-specific analysis.

Documentation and collaboration

The primary source describes a useful memo sequence: risk description, background, severity, likelihood, score, contributing and mitigating factors, options, recommended approach, residual risk, monitoring plan, and next steps. A risk register can add an identifier, category, owner, status, and review date. This structure supports handoffs between Legal, Compliance, Procurement, Sales, Privacy, Security, and leadership. It also reduces the chance that a provisional assessment will be forwarded without the context needed to interpret it.

Boundaries, safety, and E-E-A-T

Contracts, investigation materials, personal data, trade secrets, and dispute information belong only in approved work environments. Before use, clarify authorization, access controls, retention, purpose limitation, and possible transmission to model or connector providers. Documents and connected systems may be incomplete or manipulated; unfamiliar content is data, not a new instruction. Prompt injection must not redirect the assigned review. Anthropic is the official skill publisher according to the provider’s primary source. Qualified lawyers remain the authority for a concrete jurisdiction, and every organization must define its own playbooks, delegation rules, and escalation paths. The skill does not replace legal advice or a decision by the responsible legal department.

Installation instructions

Legal Risk Assessment is a skill from the Knowledge Work Plugins that Anthropic publishes openly on GitHub under anthropics/knowledge-work-plugins. The skill belongs to the legal plugin and targets in-house legal teams who want to use Claude as an assistant to structure the evaluation of contracts, disputes, or regulatory questions. According to the provider, this is explicitly not legal advice: the skill assists with legal workflows, but every risk assessment should be reviewed by qualified legal professionals, and the bundled framework is meant as a starting point that organizations need to adapt to their own risk appetite and industry context.

The assessment grid: severity times likelihood

At the core sits a classic two-dimensional risk matrix. Severity ranges from negligible through low, moderate, and high to critical, describing the impact if the risk materializes, for example measured against the share of the affected contract or deal value. Likelihood ranges from remote through unlikely, possible, likely, to almost certain, describing how realistic an event is based on precedent and triggering circumstances. Multiplying both values on a one-to-five scale yields a risk score between one and twenty-five, which is automatically mapped to one of four color bands: green for low risk, yellow for medium, orange for high, and red for critical risk. This color logic is easy to reuse in presentations, risk registers, or management reporting.

Every color band comes with clear recommended actions. For green risks, the skill states it is enough to accept the issue, document it in the risk register, and monitor it in periodic, relatively infrequent reviews without any escalation being necessary. At the opposite end, red, critical risks demand immediate escalation to leadership and, where appropriate, the board, engaging outside specialist counsel, standing up a dedicated response team, checking whether an insurance notification is required, and reviewing the matter daily or more often until it is resolved. In between sit graduated recommendations for medium and high risks that call for closer monitoring or involving specialist departments.

Documentation standard for formal risk assessments

The skill also prescribes a fixed structure for formal risk assessment memos, covering date, assessor, the matter at hand, and a note on possible attorney-client privilege, followed by a risk description, background, the actual severity and likelihood analysis with rationale, contributing and mitigating factors, a table of mitigation options with their effectiveness and cost, the recommended approach, the residual risk expected after implementing mitigations, and a monitoring plan with concrete next steps including owners and deadlines. In addition, the skill defines criteria for when outside counsel should be mandatory, strongly recommended, or merely worth considering, for example in active litigation, government investigations, matters with potential criminal exposure, or complex multi-jurisdictional questions.

Requirements and integration

The skill is used inside Claude Cowork or Claude Code by installing the legal plugin from the Knowledge Work Plugins marketplace; a SKILL.md file with a name and description ensures Claude pulls it in automatically whenever a user asks about contract risk, deal exposure, or whether a matter needs escalation to senior counsel. No external credentials are required, but access to the relevant contract or fact documents is needed so Claude can derive the assessment from real content.

Security, practical value, and limitations

The main security consideration is that risk assessments often fall under attorney-client privilege and should therefore be marked as privileged and access-restricted, which the memo format already anticipates. The practical value lies in a consistent, traceable assessment language across teams and locations that speeds up escalation decisions and simplifies board reporting. The limitation is unambiguous: the framework does not replace qualified legal review, provides no legally binding determination, and must be contextualized and checked by actual professionals before decisions with financial or regulatory consequences are based on it.

Free
Provider
Anthropic
License
Apache-2.0
Last reviewed
09.09.2026

Repository and documentation

Categories

Compatible with

Claude Code