{ "schemaVersion": "1.0", "item": { "slug": "consensus-permission-escalation-guard", "name": "consensus-permission-escalation-guard", "source": "tencent", "type": "skill", "category": "安全合规", "sourceUrl": "https://clawhub.ai/kaicianflone/consensus-permission-escalation-guard", "canonicalUrl": "https://clawhub.ai/kaicianflone/consensus-permission-escalation-guard", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/consensus-permission-escalation-guard", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=consensus-permission-escalation-guard", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SECURITY-ASSURANCE.md", "SKILL.md", "examples/input.json", "metadata.json", "package-lock.json" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/consensus-permission-escalation-guard" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/consensus-permission-escalation-guard", "agentPageUrl": "https://openagent3.xyz/skills/consensus-permission-escalation-guard/agent", "manifestUrl": "https://openagent3.xyz/skills/consensus-permission-escalation-guard/agent.json", "briefUrl": "https://openagent3.xyz/skills/consensus-permission-escalation-guard/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "consensus-permission-escalation-guard", "body": "consensus-permission-escalation-guard is the final safety gate before privilege elevation is applied." }, { "title": "What this skill does", "body": "validates escalation requests against a strict input schema (reject unknown fields)\nevaluates hard-block and rewrite policy flags for IAM risk patterns\nruns persona-weighted voting (or aggregates external votes)\nreturns one of: ALLOW | BLOCK | REQUIRE_REWRITE\nwrites decision artifacts for replay/audit" }, { "title": "Decision policy shape", "body": "Hard-block examples:\n\nwildcard permissions (*, : *, broad owner/admin jumps)\nmissing ticket reference when required\nbreak-glass escalation without incident reference\nseparation-of-duties conflicts (e.g., create + approve authority)\n\nRewrite examples:\n\nweak or non-actionable justification\ntemporary duration exceeds policy limit\nproduction escalation requires explicit human confirmation gate" }, { "title": "Runtime and safety model", "body": "runtime binaries: node, tsx\nnetwork behavior: none in deterministic guard logic\nenvironment config read by this package: CONSENSUS_STATE_FILE, CONSENSUS_STATE_ROOT\nfilesystem writes: consensus board/state artifacts under configured state path" }, { "title": "Invoke contract", "body": "invoke(input, opts?) -> Promise\n\nModes:\n\nmode=\"persona\" (default): uses local deterministic persona defaults for internal voting\nmode=\"external_agent\": consume external_votes[], then aggregate and enforce policy deterministically" }, { "title": "Install", "body": "npm i consensus-permission-escalation-guard" }, { "title": "Quick start", "body": "node --import tsx run.js --input ./examples/input.json" }, { "title": "Tests", "body": "npm test\n\nTest coverage includes schema rejection, hard-block paths, rewrite paths, allow paths, idempotent retries, and external-agent aggregation behavior.\n\nNote: this skill depends on consensus-guard-core for aggregation/state helpers; review that package alongside this one for full runtime auditability.\n\nSee also: SECURITY-ASSURANCE.md for threat model, runtime boundaries, and deployment hardening guidance." } ], "body": "consensus-permission-escalation-guard\n\nconsensus-permission-escalation-guard is the final safety gate before privilege elevation is applied.\n\nWhat this skill does\nvalidates escalation requests against a strict input schema (reject unknown fields)\nevaluates hard-block and rewrite policy flags for IAM risk patterns\nruns persona-weighted voting (or aggregates external votes)\nreturns one of: ALLOW | BLOCK | REQUIRE_REWRITE\nwrites decision artifacts for replay/audit\nDecision policy shape\n\nHard-block examples:\n\nwildcard permissions (*, : *, broad owner/admin jumps)\nmissing ticket reference when required\nbreak-glass escalation without incident reference\nseparation-of-duties conflicts (e.g., create + approve authority)\n\nRewrite examples:\n\nweak or non-actionable justification\ntemporary duration exceeds policy limit\nproduction escalation requires explicit human confirmation gate\nRuntime and safety model\nruntime binaries: node, tsx\nnetwork behavior: none in deterministic guard logic\nenvironment config read by this package: CONSENSUS_STATE_FILE, CONSENSUS_STATE_ROOT\nfilesystem writes: consensus board/state artifacts under configured state path\nInvoke contract\ninvoke(input, opts?) -> Promise\n\nModes:\n\nmode=\"persona\" (default): uses local deterministic persona defaults for internal voting\nmode=\"external_agent\": consume external_votes[], then aggregate and enforce policy deterministically\nInstall\nnpm i consensus-permission-escalation-guard\n\nQuick start\nnode --import tsx run.js --input ./examples/input.json\n\nTests\nnpm test\n\n\nTest coverage includes schema rejection, hard-block paths, rewrite paths, allow paths, idempotent retries, and external-agent aggregation behavior.\n\nNote: this skill depends on consensus-guard-core for aggregation/state helpers; review that package alongside this one for full runtime auditability.\n\nSee also: SECURITY-ASSURANCE.md for threat model, runtime boundaries, and deployment hardening guidance." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/kaicianflone/consensus-permission-escalation-guard", "publisherUrl": "https://clawhub.ai/kaicianflone/consensus-permission-escalation-guard", "owner": "kaicianflone", "version": "0.1.13", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/consensus-permission-escalation-guard", "downloadUrl": "https://openagent3.xyz/downloads/consensus-permission-escalation-guard", "agentUrl": "https://openagent3.xyz/skills/consensus-permission-escalation-guard/agent", "manifestUrl": "https://openagent3.xyz/skills/consensus-permission-escalation-guard/agent.json", "briefUrl": "https://openagent3.xyz/skills/consensus-permission-escalation-guard/agent.md" } }