AC agent-privacy-check
Audit an AI agent's reachable data, external data paths, and untrusted instructions, then explain the result in plain language with Low, Medium, High, or Critical severity. Use when a user asks what an agent can see, where data may go, whether a skill, plugin, or tool is safe, or how to reduce agent privacy risk across Codex, Claude Code, or another agent.
Audit an AI agent's reachable data, external data paths, and untrusted instructions, then explain the result in plain language with Low, Medium, High, or…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 · 0
✓ No critical or high findings
Files scanned: 8. 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 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 12 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2944 tokens
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +3Description length 358: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 33 items
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.