DC pr-gardening
Discover the pull requests this Paperclip instance opened (never community contributions), report what each is for and how confident we are that it is merge-ready, and automatically drive the non-ready ones back to green with /prepare-paperclip-pr — without ever merging.
Discover the pull requests this Paperclip instance opened (never community contributions), report what each is for and how confident we are that it is…
As a process C 57/100 · Has gaps — References files that are not bundled: /PAP/issues/PAP-310
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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.
How to improve
- 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
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-redirectable-api-keyscripts/find-candidates.mjs:28Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bash(curl:*)allowed-tools: Bash(node:*) Bash(gh:*) Bash(curl:*)
Files scanned: 6. 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: /PAP/issues/PAP-310 - note
edit-residuethe text marks something as outdated (lines 58): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 57/100
- 0Tools and files. 1 referenced file(s) missing: /PAP/issues/PAP-310
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 34 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3170 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
- low 11 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)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 271: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 5 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
scripts/check-readiness.mjs | ничего за пределами своей папки |
scripts/find-candidates.mjs | ничего за пределами своей папки |
scripts/lib.mjs | ничего за пределами своей папки |
scripts/pr-gardening.test.mjs | ничего за пределами своей папки |
scripts/render-report.mjs | ничего за пределами своей папки |
13 Oct 2026