AC autonomous-procurement-agent
Enterprise procurement quote parsing and fraud detection. Use when: (1) A supplier quote arrives as messy plain-text, OCR scan, or SAP export, (2) Cross-platform invoice reconciliation is needed across CNY/USD/EUR, (3) B2B finance teams need real-time risk auditing on vendor submissions, (4) Approval escalation thresholds need to be enforced automatically. Handles non-standard formats with dual-engine AI (regex + GPT-4o fallback), F1/F2/F3 fraud detection, and Lemon Squeezy MoR subscription.
As a process C 62/100 · Has gaps — weak spots: inputs and preconditions, 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 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-pipe-to-shellmanifest.json:19Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)"Install method changed from curl|bash to git clone + npm install",
code literal
Files scanned: 10. 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 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3276 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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)
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 496: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 17 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.