CF arianna-openclaw-integration
Integrates the Playfilo shared-memory DAG into OpenClaw via pnpm patch on the embedded pi-coding-agent. Layers on top of arianna-pi-integration.
As a process F 40/100 · Will not run — References files that are not bundled: ../pi-integration-skill/SKILL.md, ../pi-integration-skill/filo/patches/tobe-v2-spec.md
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.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 2
-
high Instruction override
en-fake-system-promptSKILL.md:63Fake system prompt injected into content### System Prompt Override Chain
Medium and low: 1
-
medium Instruction override
en-fake-system-promptSKILL.md:100Fake system prompt injected into content (quoted — discussed, not commanded)**No adaptation is needed** — OpenClaw's system prompt override, model selection, and tool registration all flow through `agent.state`, which the lazy callback reads at persist-time. The full OpenClaw
quoted
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: ../pi-integration-skill/SKILL.md - warning
missing-refreference to a missing file: ../pi-integration-skill/filo/patches/tobe-v2-spec.md
Process rating: all ten parameters 40/100
- 0Tools and files. 2 referenced file(s) missing: ../pi-integration-skill/SKILL.md, ../pi-integration-skill/filo/patches/tobe-v2-spec.md
- 0Result and completion. Does not say what the result is
- 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. 24 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2427 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 144: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.