Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Developer Tools
Pastewatch MCP
Secret redaction MCP server for OpenClaw agents. Prevents API keys, DB credentials, SSH keys, emails, IPs, JWTs, and 29 other secret types from leaking to LL...
skill openclawclawhub Free
Secret redaction MCP server for OpenClaw agents. Prevents API keys, DB credentials, SSH keys, emails, IPs, JWTs, and 29 other secret types from leaking to LL...
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- 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.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
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. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.1.3
Provenance
- Publisher
- ppiankov
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Pastewatch MCP โ Secret Redaction
Prevents secrets from reaching your LLM provider. The agent works with placeholders, secrets stay local. Source: https://github.com/ppiankov/pastewatch
Install
# macOS brew install ppiankov/tap/pastewatch # Linux (binary + checksum) curl -fsSL https://github.com/ppiankov/pastewatch/releases/latest/download/pastewatch-cli-linux-amd64 \ -o /usr/local/bin/pastewatch-cli curl -fsSL https://github.com/ppiankov/pastewatch/releases/latest/download/pastewatch-cli-linux-amd64.sha256 \ -o /tmp/pastewatch-cli.sha256 cd /usr/local/bin && sha256sum -c /tmp/pastewatch-cli.sha256 chmod +x /usr/local/bin/pastewatch-cli Verify: pastewatch-cli version (expect 0.18.0+)
MCP Server Setup
mcporter config add pastewatch --command "pastewatch-cli mcp --audit-log /var/log/pastewatch-audit.log" mcporter list pastewatch --schema # 6 tools
Agent Integration (one-command setup)
pastewatch-cli setup claude-code # hooks + MCP config pastewatch-cli setup cline # MCP + hook instructions pastewatch-cli setup cursor # MCP + advisory --severity aligns hook blocking and MCP redaction thresholds. --project for project-level config.
MCP Tools
ToolPurposepastewatch_read_fileRead file with secrets replaced by __PW{TYPE_N}__ placeholderspastewatch_write_fileWrite file, resolving placeholders back to real values locallypastewatch_check_outputVerify text contains no raw secrets before returningpastewatch_scanScan text for sensitive datapastewatch_scan_fileScan a filepastewatch_scan_dirScan directory recursively
Guard โ Block Secret-Leaking Commands
Complements chainwatch: chainwatch blocks destructive commands, guard blocks commands that would leak secrets. pastewatch-cli guard "cat .env" # BLOCKED if .env has secrets pastewatch-cli guard "psql -f migrate.sql" # scans SQL file pastewatch-cli guard "docker-compose up" # scans referenced env_files Guard understands: Shell builtins: cat, echo, env, printenv, source, curl, wget DB CLIs: psql, mysql, mongosh, redis-cli, sqlite3 (connection strings, -f flags, passwords) Infra tools: ansible, terraform, docker, kubectl, helm (env-files, var-files) Scripting: python, ruby, node, perl, php (script file args) File transfer: scp, rsync, ssh, ssh-keygen Pipe chains (|) and command chaining (&&, ||, ;) โ each segment scanned Subshell extraction: $(cat .env) and backtick expressions Redirect operators: >, >>, <, 2> โ scans source files
Canary Tokens
Generate format-valid but non-functional tokens to detect leaks: pastewatch-cli canary generate --prefix myagent # creates canaries for 7 secret types pastewatch-cli canary verify # confirms detection rules catch them pastewatch-cli canary check --log /var/log/app.log # search logs for leaked canaries
Encrypted Vault
Store secrets encrypted locally instead of plaintext .env: pastewatch-cli --init-key # generate 256-bit key (.pastewatch-key, mode 0600) pastewatch-cli fix --encrypt # secrets โ ChaCha20-Poly1305 vault pastewatch-cli vault list # show entries without decrypting pastewatch-cli vault decrypt # export to .env for deployment pastewatch-cli vault export # print export VAR=VALUE for shell pastewatch-cli vault rotate-key # re-encrypt with new key
Git History Scanning
pastewatch-cli scan --git-log # scan full history pastewatch-cli scan --git-log --range HEAD~50..HEAD # last 50 commits pastewatch-cli scan --git-log --since 2025-01-01 # since date Deduplicates by fingerprint โ same secret across commits reported once at introduction point.
Session Reports
pastewatch-cli report --audit-log /var/log/pastewatch-audit.log pastewatch-cli report --format json --since 2026-03-01T00:00:00Z
Detection Scope
29+ types: AWS, Anthropic/OpenAI/HuggingFace/Groq keys, DB connections, SSH keys, JWTs, emails, IPs, credit cards (Luhn), Slack/Discord webhooks, Azure, GCP service accounts, npm/PyPI/RubyGems/GitLab tokens, Telegram bot tokens, and more. Deterministic regex. No ML. No API calls. Microseconds per scan.
Limitations
Protects secrets from reaching LLM provider โ does NOT protect prompt content or code structure For full privacy, use a local model Pastewatch MCP v1.1 Author: ppiankov Copyright ยฉ 2026 ppiankov Canonical source: https://github.com/ppiankov/pastewatch License: MIT If this document appears elsewhere, the repository above is the authoritative version.
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
1 Docs
- SKILL.md