BB stock-sentiment
Sentiment and smart-money positioning for US stocks.
Sentiment and smart-money positioning for US stocks.
As a process B 66/100 · Nearly there — weak spots: result and completion, running it twice
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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 Concealment
en-hide-from-userSKILL.md:265Instruction to hide actions from the userSynthesize the setup as educational context: "$AAPL earnings in 5d: sentiment +0.22 over 30d and trending up; insiders net sellers (2 sells, 0 buys); EPS consensus $1.52 (range $1.48 to $1.55, 28 anal
Medium and low: 2
-
medium Exfiltration
net-credential-useSKILL.md:73Credential used in a network call (verify the destination is the intended service)curl -s -H "X-SentiSense-API-Key: $SENTISENSE_API_KEY" \
-
low Exfiltration
net-credential-useSKILL.md:296Credential used in a network call (verify the destination is the intended service) (security demo / example; quoted — discussed, not commanded)1. **Reachability and auth.** Every endpoint here takes an API key, so one call checks both: `curl -s -o /dev/null -w "%{http_code}" -H "X-SentiSense-API-Key: $SENTISENSE_API_KEY" "https://app.sentisedemoquoted
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7375 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "requires" - note
frontmatter-keyunknown frontmatter key "primaryEnv"
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7375 tokens
- 100Steps. 51 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- 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
- +3Description length 52: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 15 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (4 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.