Borrowing it
Nothing to install: this file belongs to putervision/WebCrypt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/putervision/WebCrypt/main/.agents/skills/webcrypt-mcp/SKILL.mdgit clone --depth 1 https://github.com/putervision/WebCryptWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/putervision/webcrypt/webcrypt-mcp)<a href="https://agentmods.dev/skills/putervision/webcrypt/webcrypt-mcp"><img src="https://agentmods.dev/badge/skills/putervision/webcrypt/webcrypt-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/putervision/webcrypt/webcrypt-mcp"><img src="https://agentmods.dev/badge/skills/putervision/webcrypt/webcrypt-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 22 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 24 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 25 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 26 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 27 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 28 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium MCP Rug Pull · line 48 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01070 |
| Opus 5.5 | $0.00023 | $0.00428 |
| Sonnet 5.5 | $0.00012 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
webcrypt-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
95% identical to webcrypt-mcp — 26 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cryptographic Memory & Vault Tooling (webcrypt-mcp)
This project provides webcrypt-mcp, a native Model Context Protocol server for zero-dependency AES-256-GCM encryption, RSA-4096 hybrid public-key encryption, digital signatures, cryptographic hashes, and post-quantum cryptography.
1. Mandatory Workflow & Priority
- Confidential Artifacts: Whenever saving sensitive credentials, tokens, or private workflow states, encrypt them using
encrypt_payload(mode: "data", password: "...")orencrypt_payload(mode: "symmetric", password: "..."). - Key Management: Use
manage_keys(action: "generate", type: "rsa" | "ecdh" | "ecdsa" | "rsa-pss" | "hmac")to generate cryptographically strong JWK-formatted keys for inter-agent communication. - Integrity & Signatures: Before completing tasks that produce verifiable evidence (such as evidence packs or release binaries), compute signatures or HMAC tags using
sign_verify(action: "sign", algorithm: "ECDSA" | "HMAC"). - Triple Memory Triad:
state-memory-mcp: Workflow state tracking.vision-memory-mcp: Visual state caching.webcrypt-mcp: Encryption of sensitive DAG nodes, visual cache database vaults, and signature verification.
2. Complete Tool Reference
| Tool Name | Key Inputs | Description |
|---|---|---|
encrypt_payload |
mode ('symmetric' | 'asymmetric' | 'data'), data, password?, public_key_jwk? |
Encrypt plaintext, JSON object, or binary data. |
decrypt_payload |
mode ('symmetric' | 'asymmetric' | 'data'), ciphertext, password?, private_key_jwk? |
Decrypt ciphertext back to plaintext or structured JSON. |
manage_keys |
action ('generate' | 'generate_random_password'), type ('rsa' | 'ecdh' | 'ecdsa' | 'rsa-pss' | 'hmac'), modulusLength?, namedCurve?, length? |
Generate cryptographic keys (JWK format) or secure random passwords. |
crypto_hash |
algorithm ('SHA-256' | 'SHA-384' | 'SHA-512' | 'SHA3-256' | 'SHA3-512'), data, encoding ('hex' | 'base64') |
Compute cryptographic hash digests. |
sign_verify |
action ('sign' | 'verify'), algorithm ('ECDSA' | 'RSA-PSS' | 'HMAC' | 'HMAC-SHA3'), data, signature?, password?, key_jwk? |
Sign or verify messages with ECDSA, RSA-PSS, or HMAC. |
pqc_kem_sign |
action ('generate_kyber_keypair' | 'kyber_encapsulate' | 'kyber_decapsulate' | 'hybrid_encapsulate' | 'hybrid_decapsulate' | 'generate_dilithium_keypair' | 'dilithium_sign' | 'dilithium_verify'), level?, public_key_b64?, private_key_b64?, ... |
Post-quantum Kyber KEM, Dilithium signatures, and Hybrid KEM. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 49 lines · 58 tokens per session scan A 6e091f5bd787
webcrypt-mcp is a skill published in the GitHub repository putervision/WebCrypt (14 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,070 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to webcrypt-mcp, differing in 26 lines, and is treated as a copy.
webcrypt-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| webcrypt-mcpputervision/WebCrypt | Skill | 14 | 2mo ago | MIT | A | 58 | Claude Code, Codex |
| implementing-aes-encryption-for-data-at-restxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | A | 52 | Claude Code, Codex |
| implementing-end-to-end-encryption-for-messagingxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | A | 49 | Claude Code, Codex |
| implementing-envelope-encryption-with-aws-kmsxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | A | 55 | Claude Code, Codex |
| cryptography-expertpersonamanagmentlayer/pcl | Skill | 44 | 11d ago | Apache-2.0 | A | 72 | Claude Code |
| analyzing-ransomware-encryption-behaviormeltedinhex/analyst-ai-pack | Skill | 24 | 4mo ago | Apache-2.0 | A | 72 | Claude Code, Codex |
| implementing-aes-encryption-for-data-at-restNjones17/AI-agent-master-cyber-skills-list | Skill | 25 | 8mo ago | none | A | 52 | Claude Code, Codex |