DC pyre-world

Agent-first faction warfare kit for Torch Market. Game-semantic wrapper over torchsdk. The game IS the economy. There is no separate game engine — Torch Market is the engine. Faction founding, alliance, betrayal, trade, trade — all of it already exists as on-chain Solana primitives. The pyre_world program (2oai1EaDnFcSNskyVwSbGkUEddxxfUSsSVRokE31gRfv) is a separate on-chain program for agent memory, personality, and identity — independent from the torch_market economic layer.

Not recommendedlow grade D

ClawHub Agent Skills author: mr brightside v10.2.0 MIT-0 58 files body ≈ 8 097 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

Procedure AI and agents Infrastructuretype and topics are labelled automatically from the skill text

Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode

JSON

Technical rating

59/100

safety, quality, tests

Safety 60%: 57
Quality 40%: 62
Run on models: none yet

Process rating

50/100

Has gaps

Result and completion w 14: 0
Inputs and preconditions w 11: 0
When it triggers w 12: 20

the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

How to improve

Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.

For the model run — optional

Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 39

✓ No critical or high findings

Medium and low: 39

medium Risky intent intent-wallet-secrets SKILL.md:530

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
1. **Never ask a user for their private key or seed phrase.**
```
low Secrets in code secret-high-entropy-token agent.json:72

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"program_id": "8hbU…BeT",
```
quoted
low Secrets in code secret-high-entropy-token agent.json:73

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"pyre_world_program_id": "2oai…Rfv",
```
quoted
low Secrets in code secret-high-entropy-token agent.json:236

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"wallet": "8cpW…nMa",
```
quoted
low Secrets in code secret-high-entropy-token agent.json:237

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
"pda": "2rNk…Mmb",
```
detector
low Secrets in code secret-high-entropy-token audit_program_pyre.md:12

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| Program ID | `2oai…Rfv` |
```
table
low Secrets in code secret-high-entropy-token audit_program_pyre.md:19

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
**Relationship to torch_market:** pyre_world is a **separate, independent program** from the torch_market protocol (`8hbU…BeT`). There is no CPI between the two pro
```
quoted
low Secrets in code secret-high-entropy-token audit_program_torch.md:18

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
Program ID: `8hbU…BeT`
```
quoted
low Secrets in code secret-high-entropy-token audit_program_torch.md:1033

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
3. **Transactions are deterministic.** Built from the Anchor IDL against the on-chain program. All accounts are PDA-derived. Verify the program ID (`8hbU…BeT`) if y
```
quoted
low Secrets in code secret-high-entropy-token audit_sdk.md:6

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
**On-Chain Program:** `8hbU…BeT` (V10.1.1)
```
quoted

low Secrets in code secret-high-entropy-token audit_sdk.md:485

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)

31. **V4.1.0 VersionedTransaction + Quote-Driven Trading** — Major SDK improvement, no on-chain program changes. All transaction builders now return `VersionedTransaction` (v0 messages) instead of leg

quoted

low Secrets in code secret-high-entropy-token audit_sdk.md:506

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
**On-Chain Version:** V10.1.1 (Program ID: `8hbU…BeT`)
```
quoted
low Secrets in code secret-high-entropy-token lib/kit/pyre_world.json:2

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "2oai…Rfv",
```
quoted
low Secrets in code secret-high-entropy-token lib/kit/util.js:22

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'3YVQ…Rpw',
```
quoted
low Secrets in code secret-high-entropy-token lib/kit/util.js:23

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'6wnF…2pw',
```
quoted
low Secrets in code secret-high-entropy-token lib/kit/util.js:24

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'DNBg…5pw',
```
quoted
low Secrets in code secret-high-entropy-token lib/kit/util.js:25

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'FGdf…2pw',
```
quoted
low Secrets in code secret-high-entropy-token lib/kit/util.js:26

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
'9TTs…Fpw',
```
quoted
low Secrets in code secret-high-entropy-token lib/kit/vanity.js:19

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const TOKE…_ID = new web3…Key('Toke…uEb');
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:6

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
exports.PROGRAM_ID = new web3…Key('8hbU…BeT');
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:14

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
? 'CPMD…kCW'
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:15

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
: 'CPMM…P1C');
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:18

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
exports.WSOL_MINT = new web3…Key('So11…112');
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/constants.js:21

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
? '9zSz…Bj6'
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/tokens.js:395

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
programId === 'Memo…cHr' ||
```
detector
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:2

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "8hbU…BeT",
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:914

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "ATok…knL"
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:1617

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "ATok…knL"
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:1625

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "Sysv…111"
```
quoted
low Secrets in code secret-high-entropy-token lib/torchsdk/torch_market.json:2258

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"address": "ATok…knL"
```
quoted

low Secrets in code secret-high-entropy-token SKILL.md:4

High-entropy token-like string (may be an id, hash or a credential)

description: Agent-first faction warfare kit for Torch Market. Game-semantic wrapper over torchsdk. The game IS the economy. There is no separate game engine — Torch Market is the engine. Faction foun

low Secrets in code secret-high-entropy-token SKILL.md:47

High-entropy token-like string (may be an id, hash or a credential)
```
program-id: 8hbU…BeT
```
low Secrets in code secret-high-entropy-token SKILL.md:48

High-entropy token-like string (may be an id, hash or a credential)
```
pyre-world-program-id: 2oai…Rfv
```
low Secrets in code secret-high-entropy-token SKILL.md:130

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
isPyreMint('7xKX…Epw'); // true
```
quoted
low Secrets in code secret-high-entropy-token SKILL.md:131

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
isPyreMint('9nRf…Ktm'); // false (torch token)
```
quoted
low Secrets in code secret-high-entropy-token verification_pyre.md:7

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
**Program ID:** `2oai…Rfv`
```
quoted
low Secrets in code secret-high-entropy-token verification_pyre.md:119

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| Program ID | `2oai…Rfv` | pyre_world program address |
```
table
low Risky intent intent-offensive-security verification_torch.md:212

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
| **CPI safety** | Reentrancy via Raydium CPIs, privilege escalation | Cross-program invocation is outside arithmetic scope |
```
low Risky intent intent-offensive-security verification_torch.md:223

Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
```
3. **CPI safety** -- can Raydium CPIs be exploited for reentrancy or privilege escalation?
```

Files scanned: 58. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

warning description-no-when description does not say WHEN to use the skill (no "use when")
warning body-long SKILL.md body ≈ 8097 tokens (recommended < 5000); move details to references/
note frontmatter-key unknown frontmatter key "requires"

Process rating: all ten parameters 50/100

0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
20When it triggers. No condition that starts the skill
40Consistency. Frontmatter name (pyre-world) differs from the folder (pyreworld)
40Execution cost. Instruction body is 8097 tokens: crowds the task out of the window
60Tools and files. Uses tools (web, node) that frontmatter does not declare
100Steps. 165 steps
100Failures and branches. 6 branches, has a failure section
100Running it twice. Mutating operations check current state
100Progress reporting. Reports progress

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

+5Description has no quoted example phrases that should trigger the skill
+4Description does not say when NOT to use the skill (false activations)
+3Output format is not stated: the model decides each time
+2Single-language instructions
+3Description length 480: enough signal without eating the budget
+4Structure: 43 headings
+3Step-by-step instructions: 165 items
+4Has examples (11 code blocks)
+1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

External checks

ClawHub: clean

This is a disclosed Solana game/DeFi toolkit that can build high-impact financial transactions, but the risky capabilities are visible and purpose-aligned rather than hidden.

LLM: benign (medium) · VirusTotal: · 29 May 2026

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 58

agent.json 12K
audit_program_pyre.md 12K
audit_program_torch.md 82K
audit_sdk.md 42K
lib/kit/index.d.ts 4K
lib/kit/index.js 8K
lib/kit/providers/action.provider.d.ts 3K
lib/kit/providers/action.provider.js 13K
lib/kit/providers/intel.provider.d.ts 2K
lib/kit/providers/intel.provider.js 20K
lib/kit/providers/mapper.provider.d.ts 7K
lib/kit/providers/mapper.provider.js 5K
lib/kit/providers/registry.provider.d.ts 1K
lib/kit/providers/registry.provider.js 10K
lib/kit/providers/state.provider.d.ts 2K
lib/kit/providers/state.provider.js 14K
lib/kit/pyre_world.json 17K
lib/kit/types/action.types.d.ts 3K
lib/kit/types/action.types.js 0K
lib/kit/types/intel.types.d.ts 1K
lib/kit/types/intel.types.js 0K
lib/kit/types/mapper.types.d.ts 2K
lib/kit/types/mapper.types.js 1K
lib/kit/types/registry.types.d.ts 1K
lib/kit/types/registry.types.js 0K
lib/kit/types/state.types.d.ts 4K
lib/kit/types/state.types.js 0K
lib/kit/types.d.ts 12K
lib/kit/types.js 0K
lib/kit/util.d.ts 1K
lib/kit/util.js 7K
lib/kit/vanity.d.ts 1K
lib/kit/vanity.js 6K
lib/torchsdk/constants.d.ts 2K
lib/torchsdk/constants.js 7K
lib/torchsdk/ephemeral.d.ts 1K
lib/torchsdk/ephemeral.js 1K
lib/torchsdk/gateway.d.ts 1K
lib/torchsdk/gateway.js 2K
lib/torchsdk/index.d.ts 3K
lib/torchsdk/index.js 9K
lib/torchsdk/program.d.ts 6K
lib/torchsdk/program.js 14K
lib/torchsdk/quotes.d.ts 1K
lib/torchsdk/quotes.js 9K
lib/torchsdk/said.d.ts 1K
lib/torchsdk/said.js 4K
lib/torchsdk/tokens.d.ts 4K
lib/torchsdk/tokens.js 40K
lib/torchsdk/torch_market.json 269K
lib/torchsdk/transactions.d.ts 14K
lib/torchsdk/transactions.js 85K
lib/torchsdk/types.d.ts 12K
lib/torchsdk/types.js 0K
skill-card.md 3K
SKILL.md 34K
verification_pyre.md 7K
verification_torch.md 21K

Frontmatter

version: 10.2.0

license: MIT

disable-model-invocation: true

requires: {"env":[{"name":"SOLANA_RPC_URL","required":true},{"name":"SOLANA_PRIVATE_KEY","required":false},{"name":"TORCH_NETWORK"

metadata: {"clawdbot":{"requires":{"env":[{"name":"SOLANA_RPC_URL","required":true},{"name":"SOLANA_PRIVATE_KEY","required":false}

compatibility: REQUIRED: SOLANA_RPC_URL (HTTPS Solana RPC endpoint). OPTIONAL: SOLANA_PRIVATE_KEY (disposable controller keypair -- mus

Dates

In catalog since 6 Mar 2026

Updated in catalog 11 May 2026

First seen here 10 Sept 2026

Last analysis 11 Sept 2026, 02:39 UTC

Last seen in crawl 13 h ago

Score history

Date		Score	Safety	Qual.
10 Sept 2026	D	59	57	62