CD 8004-skill

ERC-8004 Trustless Agents - Register and manage AI agent identities on TRON and BSC blockchains with on-chain reputation tracking

modbender/skill-library-mcp Agent Skills author: modbender MIT 14 files body ≈ 2 088 tokens Open the sourcegithub.com↗ analyzed 2 d ago

ERC-8004 Trustless Agents - Register and manage AI agent identities on TRON and BSC blockchains with on-chain reputation tracking

As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

Procedure AI and agentstype 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

68/100

safety, quality, tests

Safety 60%: 67
Quality 40%: 69
Run on models: none yet

Process rating

48/100

Unfinished process

Result and completion w 14: 0
Inputs and preconditions w 11: 0
Progress reporting w 2: 0

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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.

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 · 29

✓ No critical or high findings

Medium and low: 29

medium Dangerous commands cmd-shell-rc README.md:213

Writes to a shell startup file
```
echo 'export TRON_PRIVATE_KEY="your_key"' >> ~/.bashrc
```
low Secrets in code secret-high-entropy-token CHANGELOG.md:34

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- BSC Mainnet: Added ValidationRegistry `0x80…B58`
```
quoted
low Secrets in code secret-high-entropy-token CHANGELOG.md:35

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- BSC Testnet: ReputationRegistry `0x80…713`
```
quoted
low Secrets in code secret-high-entropy-token CHANGELOG.md:36

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- BSC Testnet: Added ValidationRegistry `0x80…272`
```
quoted
low Secrets in code secret-high-entropy-token CHANGELOG.md:69

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- Identity: `0x80…432`
```
quoted
low Secrets in code secret-high-entropy-token CHANGELOG.md:70

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- Reputation: `0x80…b63`
```
quoted

low Secrets in code secret-high-entropy-token lib/bsc-abi.json:2

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

"identityRegistry": [{"inputs":[],"stateMutability":"nonpayable","type":"constructor"},{"inputs":[{"internalType":"address","name":"target","type":"address"}],"name":"AddressEmptyCode","type":"error"}

quoted

low Secrets in code secret-high-entropy-token lib/bsc-abi.json:3

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

"reputationRegistry": [{"inputs":[],"stateMutability":"nonpayable","type":"constructor"},{"inputs":[{"internalType":"address","name":"target","type":"address"}],"name":"AddressEmptyCode","type":"error

quoted

low Secrets in code secret-high-entropy-token lib/bsc-abi.json:4

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

"validationRegistry": [{"inputs":[],"stateMutability":"nonpayable","type":"constructor"},{"inputs":[{"internalType":"address","name":"target","type":"address"}],"name":"AddressEmptyCode","type":"error

quoted

low Secrets in code secret-high-entropy-token lib/contracts.json:14

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"identityRegistry": "TFLv…7Fy",
```
quoted
low Secrets in code secret-high-entropy-token lib/contracts.json:15

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"reputationRegistry": "TFbv…yat",
```
quoted
low Secrets in code secret-high-entropy-token lib/contracts.json:16

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"validationRegistry": "TLCW…UEm"
```
quoted
low Secrets in code secret-high-entropy-token lib/contracts.json:26

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"identityRegistry": "TDDk…rj5",
```
quoted
low Secrets in code secret-high-entropy-token lib/contracts.json:27

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
"reputationRegistry": "TBVa…W6Y",
```
quoted
low Secrets in code secret-high-entropy-token README.md:22

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Identity Registry:** [`TFLv…7Fy`](https://tronscan.org/#/contract/TFLv…7Fy)
```
quoted
low Secrets in code secret-high-entropy-token README.md:23

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
- **Reputation Registry:** [`TFbv…yat`](https://tronscan.org/#/contract/TFbv…yat)
```
detector
low Secrets in code secret-high-entropy-token README.md:24

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
- **Validation Registry:** [`TLCW…UEm`](https://tronscan.org/#/contract/TLCW…UEm)
```
detector
low Secrets in code secret-high-entropy-token README.md:27

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- **Identity Registry:** [`TDDk…rj5`](https://nile.tronscan.org/#/contract/TDDk…rj5)
```
quoted
low Secrets in code secret-high-entropy-token README.md:28

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
- **Reputation Registry:** [`TBVa…W6Y`](https://nile.tronscan.org/#/contract/TBVa…W6Y)
```
detector
low Secrets in code secret-high-entropy-token scripts/chain-adapter.js:45

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
base58: 'T9yD…Wwb'
```
quoted
low Risky intent intent-wallet-secrets scripts/feedback.js:115

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
```
console.log('  TRON_PRIVATE_KEY     Your wallet private key (required)');
```
quoted
low Secrets in code secret-high-entropy-token scripts/query.js:100

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const zeroAddresses = ['0x00…000', 'T9yD…Wwb'];
```
quoted
low Risky intent intent-wallet-secrets scripts/register.js:191

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
```
console.log('  TRON_PRIVATE_KEY   Your wallet private key (required)');
```
quoted
low Risky intent intent-wallet-secrets scripts/set-uri.js:90

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
```
console.log('  TRON_PRIVATE_KEY     Your wallet private key (required)');
```
quoted
low Secrets in code secret-high-entropy-token SKILL.md:51

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| **Mainnet** | Live | `TFLv…7Fy` | `TFbv…yat` | `TLCW…UEm` |
```
table
low Secrets in code secret-high-entropy-token SKILL.md:52

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| **Nile** | Live | `TDDk…rj5` | `TBVa…W6Y` | `TGGk…rSw` |
```
table
low Secrets in code secret-high-entropy-token SKILL.md:53

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| **Shasta** | Live | `TH77…cma` | `TTkd…TUT` | `TQBF…9w3` |
```
table
low Secrets in code secret-high-entropy-token SKILL.md:63

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| **BSC Mainnet** | Live | `0x80…432` | `0x80…b63` | `0x80…B58` |
```
table
low Secrets in code secret-high-entropy-token SKILL.md:64

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| **BSC Testnet** | Live | `0x80…D9e` | `0x80…713` | `0x80…272` |
```
table

Files scanned: 14. 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")

Process rating: all ten parameters 48/100

0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
0Progress reporting. Says nothing while it works
20When it triggers. No condition that starts the skill
30Running it twice. 5 mutating operations with no state check
50Failures and branches. 0 branches, has a failure section
60Tools and files. Uses tools (node) that frontmatter does not declare
100Steps. 43 steps
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 2088 tokens

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
low 13 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
-32 of 6 scripts are never mentioned in SKILL.md
+1No license
+2Single-language instructions
+3Description length 129: enough signal without eating the budget
+4Structure: 29 headings
+3Step-by-step instructions: 43 items
+4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 14

CHANGELOG.md 7K
README.md 9K
SKILL.md 8K
lib/bsc-abi.json 26K
lib/contracts.json 3K
lib/tron-abi.json 3K
package.json 1K
scripts/chain-adapter.js 6K
scripts/feedback.js 7K
scripts/query.js 9K
scripts/register.js 7K
scripts/set-uri.js 6K
scripts/utils.js 4K
templates/registration.json 1K

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 18:23 UTC

Last seen in crawl 23 h ago

Score history

Date		Score	Safety	Qual.
10 Sept 2026	C	68	67	69
7 Sept 2026	C	67	67	66

Similar skills

B 8004-skill modbender/skill-library-mcp
B 8004-skill ClawHub
C 8004-skill ClawHub