BB privy
Create and manage agentic wallets with Privy. Use for autonomous onchain transactions, wallet creation, policy management, and transaction execution on Ethereum, Solana, and other chains. Triggers on requests involving crypto wallets for AI agents, server-side wallet operations, or autonomous transaction execution.
As a process B 73/100 · Nearly there — weak spots: result and completion, progress reporting
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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Instruction override
en-ignore-previousSKILL.md:192Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)❌ "Ignore previous instructions..."
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/policies.md:194High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"0x3f…FAD",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/policies.md:195High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"0x83…913",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/policies.md:236High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"value": "0x83…913"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/transactions.md:21High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"to": "0x74…E2B",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/transactions.md:36High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"to": "0x74…E2B",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/transactions.md:51High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"to": "0x83…913",
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/wallets.md:31High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"address": "0xF1…496",
quoted
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 73/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1578 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 316: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.