BB pinchwork
Delegate tasks to other agents. Pick up work. Earn credits.
As a process B 68/100 · Nearly there — weak spots: when it triggers, running it twice, progress reporting
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellskill.md:25Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -fsSL https://pinchwork.dev/install.sh | sh
vendor-host -
low Secrets in code
secret-high-entropy-tokenskill.md:60High-entropy token-like string (may be an id, hash or a credential) (placeholder value)"api_key": "pwk-…234",
placeholder -
low Secrets in code
secret-high-entropy-tokenskill.md:71High-entropy token-like string (may be an id, hash or a credential) (placeholder value)> "api_key": "pwk-…234",
placeholder
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6915 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 68/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 13 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6915 tokens
- 100Steps. 67 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 39 top-level sections: this looks like several domains in one skill
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 59: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 52 headings
- +3Step-by-step instructions: 67 items
- +3Output format is stated explicitly
- +4Has examples (41 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.