CF sun-to-spotify
Generate Sun audio and stream episodes to Spotify as a podcast. Uses the `sun` CLI (or HTTP API) to authenticate, mint a personal API token, create an audio job from a prompt, fetch episodes incrementally as they finish, and upload each episode sequentially to a freshly-created Spotify show.
As a process F 57/100 · Will not run — References files that are not bundled: references/cli-usage.md, references/http-api.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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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.
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 · 3
-
high Dangerous commands
cmd-pipe-to-shellcli-usage.md:14Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://sunapp-ai.github.io/sun-to-spotify/install.sh | bash
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:33Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://sunapp-ai.github.io/sun-to-spotify/install.sh | bash
Medium and low: 1
-
medium Exfiltration
net-credential-usehttp-api.md:105Credential used in a network call (verify the destination is the intended service)curl -s "$BASE/v1/public/whoami" -H "Authorization: Bearer $TOKEN"
Files scanned: 4. 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: references/cli-usage.md - warning
missing-refreference to a missing file: references/http-api.md - note
frontmatter-keyunknown frontmatter key "id" - note
frontmatter-keyunknown frontmatter key "enabled"
Process rating: all ten parameters 57/100
- 0Tools and files. 2 referenced file(s) missing: references/cli-usage.md, references/http-api.md
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 15 mutating operations with no state check
- 40Consistency. Frontmatter name (sun-to-spotify) differs from the folder (sun-to-spotify1)
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4452 tokens
- 100Steps. 21 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 21 branches, has a failure section
- 100Progress reporting. Reports progress
- 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
- low The response is described with custom markup (10 tags): a typed call is more reliable
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)
- +1No license
- +2Single-language instructions
- +3Description length 292: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 21 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.