AD copypaste-cloud
Read and create pastes on copy-paste.cloud. Fetch recent public pastes, retrieve a paste by ID, or publish new content via the public API.
As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
For the model run — optional
- 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
-
low Exfiltration
net-credential-usescripts/create_paste.sh:5Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)API_KEY="${COPYPASTE_API_KEY:?COPYPASTE_API_KEY is not set. Generate a key at https://copy-paste.cloud/developer}"vendor-hostquoted -
low Exfiltration
net-credential-usescripts/get_recent.sh:5Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)API_KEY="${COPYPASTE_API_KEY:?COPYPASTE_API_KEY is not set. Generate a key at https://copy-paste.cloud/developer}"vendor-hostquoted
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (copypaste-cloud) differs from the folder (copypaste)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 10 steps
- 100Execution cost. Instruction body is 718 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 138: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (4 code blocks)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.
External checks
ClawHub: clean
This is a straightforward pastebin integration, with the main risk being that pasted content and an API key are sent to copy-paste.cloud as part of the advertised behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026