BC emocity-biometric-scan
Face scan from the browser camera in 60 seconds: stress, a heart-rate estimate, mood, micro-expressions, eye contact, genuine smile, composure and, with the microphone on, voice tension, as a summary the agent turns into JSON. Use when the user explicitly asks for a face scan, a stress or heart-rate check from the camera, a before-and-after comparison, a challenge with friends or the deception challenge game. Optional: analyse a photo or clip the user hands over through the EmoPulse API with their own RapidAPI key from the environment; that file is uploaded. Not a medical device. Built on EmoPulse, a patented on-device perception architecture.
Face scan from the browser camera in 60 seconds: stress, a heart-rate estimate, mood, micro-expressions, eye contact, genuine smile, composure and, with the…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 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
- 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 Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash
-
low Exfiltration
net-credential-useSKILL.md:130Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)printf 'X-RapidAPI-Key: %s\n' "$EMOPULSE_RAPIDAPI_KEY" | curl -s -X POST "https://emopulse-face-analysis.p.rapidapi.com/api/v1/analyze/image" \
vendor-hostquoted
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 52/100
- 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. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (emocity-biometric-scan) differs from the folder (fitcheck-workout-readiness)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 30 steps
- 100Execution cost. Instruction body is 1594 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
- +2Single-language instructions
- +3Description length 651: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.