Agent skill · Audited from source
cease-desist
skill · anthropics/claude-for-legalApache-2.0 licenceAudited 28 Oct 2026 · source cb488a888d20
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit cb488a888d20 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Draft a cease-and-desist letter (send mode) or triage one you received (receive mode). Use when asserting your rights against an infringer with a demand letter calibrated to your enforcement posture, or when an incoming…
Cite
Cite this page
ModelsAtlas. “cease-desist (anthropics/claude-for-legal)”. Retrieved 28 Oct 2026. https://modelsatlas.com/skills/anthropics/cease-desist
Trust audit
Audit 0.4.1 · source read 28 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha cb488a888d20 · 28 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisheranthropics GitHub organizationOwner of the repository this skill is read from
- Source folderanthropics/claude-for-legal/ip-legal/skills/cease-desistThe exact folder we audited
- LicenceApache-2.0As the repository states it
- Commit pinned for this verdictcb488a888d20A new audit runs when the source changes
- Repository statusNot archivedLast push 4 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Draft a cease-and-desist letter (send mode) or triage one you received (receive mode). Use when asserting your rights against an infringer with a demand letter calibrated to your enforcement posture, or when an incoming…
--- name: cease-desist description: > Draft a cease-and-desist letter (send mode) or triage one you received (receive mode). Use when asserting your rights against an infringer with a demand letter calibrated to your enforcement posture, or when an incoming C&D needs triage into a structured options memo with a recommendation. argument-hint: "<--send | --receive> [context, counterparty, or path to incoming letter]" --- # /cease-desist Two modes. Pick one: - `/ip-legal:cease-desist --send` — draft a cease-and-desist letter calibrated to your enforcement posture. Loud gate runs before delivery. - `/ip-legal:cease-desist --receive` — triage a C&D someone sent you. Produces an options memo with a recommendation. ## Instructions 1. **Read the practice profile.** Load `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`. If it contains `[PLACEHOLDER]` markers or does not exist, stop and say: "This plugin needs setup before it can give you useful output. Run `/ip-legal:cold-start-interview` — the C&D skill depends on your enforcement posture, approval matrix, and practice-area mix, none of which are configured yet." 2. **Check matter workspaces.** Per `## Matter workspaces`: if `Enabled` is `✗`, skip — skills use practice-level context. If enabled and there is no active matter, ask: "Which matter is this for? Run `/ip-legal:matter-workspace switch <slug>` or say `practice-level`." 3. **Dispatch on `$ARGUMENTS`:** - If `--send` is present: run send mode (below). Walk through identify-the-right, identify-the-conduct, identify-the-relationship, identify-the-demand, calibrate-to-posture, draft, and the pre-delivery gate. - If `--receive` is present: run receive mode (below). Ask for the incoming letter (path or pasted text), then assess, identify exposure, present options, and write the triage memo. - If neither flag is present: ask once — "Are we sending a cease-and-desist (you're asserting) or triaging one we received (you're defending)?" — and then dispatch. 4. **Respect the gate.** In send mode, the loud gate runs before any final draft is written to disk. Do not skip it. 5. **Respect the approval matrix.** Pull the approver for the C&D row from `## Enforcement posture → Approval matrix`. Pull automatic escalations. Surface both in the gate; do not smother them. 6. **Hand off where appropriate.** In receive mode, if the recommendation is to respond firmly, offer to chain into `/ip-legal:cease-desist --send` pre-populated with the response context. If the recommendation is to pre-empt with a DJ action or TTAB cancellation, escalate to outside counsel per the practice profile's IP litigation row — do not draft. ## Examples ``` /ip-legal:cease-desist --send /ip-legal:cease-desist --receive ~/Downloads/incoming-cd-acme.pdf /ip-legal:cease-desist ``` ## Notes - The outgoing C&D does not carry the work-product header. The internal draft, the pre-send brief, and the triage memo do. - Trademark rights are territorial; the draft assumes the jurisdictions declared in your practice profile's `Registered in:` footprint. If the conduct or counterparty is somewhere else, flag before drafting. - Every `[CITE:___]` is unverified until a citator run. Source attribution tags stay on the draft. - Non-lawyer users get a one-page brief for the attorney conversation before the gate clears. --- ## Purpose A cease-and-desist letter asserts a legal right and demands that someone stop doing something. It is one of the most consequential letters an IP practice sends or receives. Sending one is a first step toward litigation — recipients can file a declaratory judgment action in a forum of their choosing, and overbroad or bad-faith assertions can be used against the sender. Receiving one starts a clock and forces a decision. This skill handles both sides with the guardrails the decision deserves. Two modes: - `--send` — you are asserting. Draft a C&D calibrated to the posture, gate before delivery. - `--receive` — you are defending. Triage the incoming letter, produce an options memo, route to matter creation if warranted. If the user does not pass a flag, ask once: "Are we sending a cease-and-desist (you're asserting) or triaging one we received (you're defending)?" > **External deliverable (send mode):** the drafted C&D is sent to counterparty. Do NOT include the `PRIVILEGED & CONFIDENTIAL — ATTORNEY WORK PRODUCT` header on the outgoing letter. Internal drafts, pre-send briefs, and triage memos keep the header per plugin config `## Outputs`. ## Jurisdiction assumption Trademark rights are territorial — a US registration does not travel. Copyright is Berne-multilateral but enforcement is jurisdiction-specific, and statutory remedies (including US §504 statutory damages) turn on local law. This skill assumes the jurisdiction declared in the matter or the practice profile's `Registered in:` footprint. If the infringing conduct, counterparty, or forum is somewhere else, flag it — the draft may not apply as written. ## Load context - `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md` → `## Enforcement posture` (posture, C&D triggers, soft-letter criteria, approval matrix, automatic escalations), `## IP practice profile` (practice area mix, registered jurisdictions, outside counsel roster), `## Outputs` (work-product header, role), `## Who's using this` (role — lawyer vs. non-lawyer) - Any C&D template or enforcement playbook referenced in the practice profile's seed documents — read it, match the structure - **Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip matter machinery — skills use practice-level context. If enabled and there is no active matter, ask: "Which matter is this for? Run `/ip-legal:matter-workspace switch <slug>` or say `practice-level`." Load the active matter's `matter.md` for matter-specific overrides (e.g., posture override, approver override). Write ou
Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit cb488a8
git clone https://github.com/anthropics/claude-for-legal git -C claude-for-legal checkout cb488a888d20
The author documents no install command, so this uses the repository directly. Our verdict covers commit cb488a888d20 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
cb488a888d20
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/anthropics/cease-desist/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
obra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions…
obra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
obra/superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Add this badge to your README
[](https://modelsatlas.com/skills/anthropics/cease-desist/)
<a href="https://modelsatlas.com/skills/anthropics/cease-desist/"><img src="https://modelsatlas.com/skills/anthropics/cease-desist/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about cease-desist
What does the cease-desist skill do?
Is cease-desist safe to install?
What can cease-desist access on my machine?
How current is this page?
Sources
- github.com/anthropics/claude-for-legal/tree/main/ip-legal/skills — the audited source at commit cb488a888d20 and every finding aboveObserved · 28 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the cease-desist skill do?
- Is cease-desist safe to install?
- What can cease-desist access on my machine?