BB dataify-google-play-store-reviews-by-url
Collect Google Play app reviews from a known Play Store app URL. Do not use for app discovery, rankings, or general Google Play search.
Collect Google Play app reviews from a known Play Store app URL.
As a process B 69/100 · Nearly there — weak spots: result and completion
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 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.
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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Dangerous commands
cmd-shell-rcSKILL.md:59Writes to a shell startup fileecho 'export DATAIFY_API_TOKEN="your_token_here"' >> ~/.bashrc
-
medium Dangerous commands
cmd-shell-rcSKILL.md:65Writes to a shell startup fileecho 'export DATAIFY_API_TOKEN="your_token_here"' >> ~/.zshrc
-
medium Dangerous commands
cmd-shell-rcSKILL.zh-CN.md:47Writes to a shell startup fileecho 'export DATAIFY_API_TOKEN="your_token_here"' >> ~/.bashrc
-
medium Dangerous commands
cmd-shell-rcSKILL.zh-CN.md:54Writes to a shell startup fileecho 'export DATAIFY_API_TOKEN="your_token_here"' >> ~/.zshrc
-
low Secrets in code
secret-password-literalscripts/task_runtime.py:38Hard-coded password / key literal (may be an example)api_key = api_key[7:].strip()
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 46 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2080 tokens
- 100Running it twice. No mutating operations
- 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
- +3Output format is not stated: the model decides each time
- -36 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 135: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 46 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.