BC magicpay
Use for MagicPay payments, funding, Memory, agent email, account readiness, optional choices and human input, or payment recovery through remote MCP.
As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
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 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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 Broad scope
meta-agent-memory-dumpreferences/memory.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensreferences/memory.md
-
medium Concealment
en-hide-from-userreferences/setup.md:131Instruction to hide actions from the user ("do not tell the user <a claim>" — honesty guidance, not concealment)Do not tell the user that a fresh task or session will open OAuth. Only when
honesty claim -
medium Concealment
en-hide-from-userreferences/statuses.md:32Instruction to hide actions from the user (detector / deny-list definition)request is missing, approval setup is blocked: do not tell the user an
detector
Files scanned: 18. 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 63/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 33 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2857 tokens
- 100Progress reporting. Reports progress
- 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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 149: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 33 items
- +4Reference files are cited in the instructions (15 of 15)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.