DB pylinter-assist
(no description)
As a process B 68/100 · Nearly there — weak spots: when it triggers, running it twice
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 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.
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
- Add a description to the frontmatter: without it the skill never triggers.
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Exfiltration
exfil-webhook-urlpylinter_assist/notifications.py:55Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)self.base_url = f"https://api.telegram.org/bot{bot_token}"quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:168Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)> committing. Do not use `curl … | sh` or copy files from a branch tip (`main`) without
quoted -
low Secrets in code
secret-aws-keyCLAUDE.md:42AWS access key ID (placeholder value)| AWS/GCP access key | HCS005 | ERROR | `AKIA…PLE` |
placeholder -
low Secrets in code
secret-aws-keyREADME.md:48AWS access key ID (placeholder value)| AWS/GCP access key | HCS005 | ERROR | `AKIA…PLE` |
placeholder -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:14Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)**Install pyenv (no `curl | sh`):**
negated -
low Secrets in code
secret-aws-keySKILL.md:260AWS access key ID (placeholder value)| AWS/GCP access key | HCS005 | ERROR | `AKIA…PLE` |
placeholder -
low Exfiltration
exfil-webhook-urlSKILL.md:405Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)webhook_url: https://discord.com/api/webhooks/...
placeholder -
low Exfiltration
exfil-webhook-urlSKILL.md:408Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)webhook_url: https://hooks.slack.com/services/...
placeholder
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger
Process rating: all ten parameters 68/100
- 30When it triggers. No condition that starts the skill
- 30Running it twice. 15 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
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3156 tokens
- 100Progress reporting. Reports progress
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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)
- +3Description length 0: 120–800 characters recommended
- -2localhost URLs: will not work for another user
- -31 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 36 headings
- +3Step-by-step instructions: 17 items
- +3Output format is stated explicitly
- +4Has examples (26 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.