CF present
Authors a narrated presentation and publishes it to a shareable watch URL. Use when asked to make a presentation, slides, a video, a deck, a slideshow, a narrated briefing, or a talk.
Authors a narrated presentation and publishes it to a shareable watch URL.
As a process F 45/100 · Will not run — References files that are not bundled: /lˈaɪv/, liv, /kˈOkOɹO/
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.
- 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 · 6
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:34Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://download.bisque.today/bisque-voice/install.sh | sh # macOS, Linux
Medium and low: 5
-
medium Exfiltration
net-redirectable-api-keyscripts/present.mjs:43Helper 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 Dangerous commands
cmd-pipe-to-shellscripts/present.mjs:464Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed): " curl -fsSL https://download.bisque.today/bisque-voice/install.sh | sh"),
code literal -
medium Dangerous commands
cmd-pipe-to-shellscripts/present.mjs:610Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"curl -fsSL https://download.bisque.today/bisque-voice/install.sh | sh",
code literal -
medium Dangerous commands
cmd-pipe-to-shellscripts/present.mjs:1378Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed): " install: curl -fsSL https://download.bisque.today/bisque-voice/install.sh | sh",
code literal -
medium Dangerous commands
cmd-pipe-to-shellscripts/present.mjs:1686Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed): " curl -fsSL https://download.bisque.today/bisque-voice/install.sh | sh"),
code literal
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: /lˈaɪv/ - warning
missing-refreference to a missing file: liv - warning
missing-refreference to a missing file: /kˈOkOɹO/ - warning
missing-refreference to a missing file: assets/hero.png
Process rating: all ten parameters 45/100
- 0Tools and files. 4 referenced file(s) missing: /lˈaɪv/, liv, /kˈOkOɹO/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 30 mutating operations with no state check
- 100Steps. 11 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3305 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 183: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (8 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.