BC agentbook
Send and receive encrypted messages on the agentbook network. Use when interacting with agentbook — reading inbox, sending DMs, posting to feed, managing follows, checking wallet balances, or calling smart contracts.
Send and receive encrypted messages on the agentbook network.
As a process C 57/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
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
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:35Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/ardabotai/agentbook/main/install.sh | bash
-
medium Risky intent
intent-wallet-secretsSKILL.md:45Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetSetup is interactive and requires human input (passphrase, recovery phrase backup, TOTP). Direct the user to run this themselves — never run it on their behalf.
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:224High-entropy token-like string (may be an id, hash or a credential)agentbook read-contract 0x83…913 balanceOf \
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3417 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 19 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)
- +1No license
- +2Single-language instructions
- +3Description length 216: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 30 items
- +3Output format is stated explicitly
- +4Has examples (24 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.