FC storj-agent

Autonomous economic agent that earns BTC & SOL by selling storage, compute, and bandwidth. Pays its own hosting, manages subagents, posts tweets, and replicates when profitable.

Blockedguard blocked the skill: signs of malicious behaviour

modbender/skill-library-mcp Agent Skills author: modbender MIT 18 files body ≈ 1 291 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Autonomous economic agent that earns BTC & SOL by selling storage, compute, and bandwidth.

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

Procedure Supabase 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

33/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 83
Run on models: none yet

Process rating

51/100

Has gaps

Result and completion w 14: 0
Inputs and preconditions w 11: 0
Failures and branches w 10: 0

the three weakest of ten parameters · all ten

Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Secrets in code

If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.

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 · 20

critical Secrets in code secret-openrouter-key mainapp.py:12

OpenRouter API key (quoted — discussed, not commanded)
```
OPENROUTER_KEY = "sk-o…c53"
```
quoted
critical Secrets in code secret-openrouter-key services/tasking.py:9

OpenRouter API key (quoted — discussed, not commanded)
```
OPENROUTER_KEY = "sk-o…c53"
```
quoted

Medium and low: 18

medium Broad scope meta-agent-memory-dump HEARTBEAT.md

Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
```
HEARTBEAT.md
```
medium Secrets in code secret-labelled-token twitterdata.txt:3

Labelled token / key literal (vendor format unknown — verify it is not a live credential)
```
ClientSecret: zJEv…z35
```
medium Secrets in code secret-labelled-token twitterdata.txt:5

Labelled token / key literal (vendor format unknown — verify it is not a live credential)
```
AccessToken: 1940…qng
```
low Secrets in code secret-labelled-token mainapp.py:15

Labelled token / key literal (vendor format unknown — verify it is not a live credential) (placeholder value)
```
ACCESS_TOKEN = "1940…qng"
```
placeholder
low Secrets in code secret-password-literal mainapp.py:15

Hard-coded password / key literal (may be an example) (placeholder value)
```
ACCESS_TOKEN = "1940…qng"
```
placeholder
low Secrets in code secret-high-entropy-token mainapp.py:16

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
ACCESS_SECRET = "Ml4W…Zkm"
```
quoted
low Secrets in code secret-high-entropy-token mainapp.py:17

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
BEARER = "AAAAAAAAAAAAAAAAAAAAABA%2B7w…61E%3DSj…sXE"
```
quoted
low Secrets in code secret-high-entropy-token mainapp.py:22

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
SUPABASE_KEY = "sb_s…ikO"
```
quoted
low Secrets in code secret-high-entropy-token mainapp.py:45

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
YOUR_WALLET = "Eib7…DQT"
```
quoted
low Obfuscation obf-base64-blob services/tasking.py:14

Long base64-looking blob (quoted — discussed, not commanded)
```
ACCESS_GRANT = "12Tg…LEx
```
quoted
low Obfuscation obf-base64-blob testingbase64.py:23

Long base64-looking blob (detector / deny-list definition; code comment; test fixture / example file)
```
#signature: 3ycM…82y
```
detectorcommentfixture
low Obfuscation obf-base64-blob testingbase64.py:25

Long base64-looking blob (code comment; test fixture / example file)
```
#data…SNp/pPqB…dCf/DzBU…c86//AwA
```
commentfixture
low Secrets in code secret-high-entropy-token testingbase64.py:25

High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file)
```
#data…SNp/pPqB…dCf/DzBU…c86//AwA
```
fixture
low Secrets in code secret-high-entropy-token twitterdata.txt:1

High-entropy token-like string (may be an id, hash or a credential)
```
ClientSecretId: MWho…jaQ
```
low Secrets in code secret-password-literal twitterdata.txt:3

Hard-coded password / key literal (may be an example)
```
ClientSecret: zJEv…z35
```
low Secrets in code secret-password-literal twitterdata.txt:5

Hard-coded password / key literal (may be an example)
```
AccessToken: 1940…qng
```
low Secrets in code secret-high-entropy-token twitterdata.txt:7

High-entropy token-like string (may be an id, hash or a credential)
```
AccessTokenSecret: Ml4W…Zkm
```
low Secrets in code secret-high-entropy-token twitterdata.txt:13

High-entropy token-like string (may be an id, hash or a credential)
```
BearerToken: AAAAAAAAAAAAAAAAAAAAABA%2B7w…prs%3DEh…PUR
```

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 51/100

0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
0Failures and branches. Linear process with no failure handling
0Progress reporting. Says nothing while it works
20When it triggers. No condition that starts the skill
30Running it twice. 7 mutating operations with no state check
100Tools and files. No external tools needed
100Steps. 41 steps
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 1291 tokens

medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
+1No license
+2Single-language instructions
+3Description length 177: enough signal without eating the budget
+4Structure: 11 headings
+3Step-by-step instructions: 41 items
+4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 18

HEARTBEAT.md 2K
MESSAGING.md 2K
SKILL.md 6K
blockchain/__init__.py 0K
blockchain/blockchain.py 7K
mainapp.py 5K
management/StorjAgent.py 1K
management/__init__.py 0K
package.json 1K
services/__init__.py 0K
services/evolution.py 0K
services/sales.py 4K
services/survival.py 0K
services/tasking.py 7K
subagents/__init__.py 0K
subagents/employees.py 2K
testingbase64.py 14K
twitterdata.txt 0K

When to use

Use this skill when: - Deploying or managing a StorJ autonomous agent - The agent needs to sell storage, compute, or bandwidth for BTC & SOL - Processing pay-and-upload requests from other agents - Generating and posting tweets as the StorJ persona - Managing subagent workers (spawn, evaluate, evolve) - Checking wallet balances or sending transactions on Bitcoin or Solana

Frontmatter

version: 2.0.0

homepage: https://bitcointalk.org/index.php?topic=53855.0

metadata: {"clawdbot":{"emoji":"🧬","requires":{"env":["OPENROUTER_KEY","TWITTER_CONSUMER_KEY","TWITTER_CONSUMER_SECRET","TWITTER_

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 18:21 UTC

Last seen in crawl 2 d ago

Score history

Date		Score	Safety	Qual.
7 Sept 2026	F	33	0	83
7 Sept 2026	F	31	0	77