CD thunder-red-team
Adversarial security review of Thunderbolt's end-to-end encryption. Attacks the security claims in docs/internals/architecture/e2ee-threat-model.md rather than reviewing code for correctness. Modes: a full sweep (`all`, or no argument) that fans every scoped pass out as a subagent then triages and refutes; a reproduce step that promotes a confirmed finding to an executed attack spec; a single read-only reasoning pass over one scope; or a live hunt against a booted local stack. Use when asked to "red team", "attack the encryption", "try to break E2EE", "run a red-team pass" or "run all red-team passes", or to validate a claim like "the server cannot read user data".
Adversarial security review of Thunderbolt's end-to-end encryption.
As a process D 49/100 · Unfinished process — References files that are not bundled: ../../../docs/internals/architecture/red-team-harness.md, scripts/org-escrow-*.ts, scripts/org-escrow-keygen.ts
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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
-
low Risky intent
intent-offensive-securitySKILL.md:10Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)when asked to "red team", "attack the encryption", "try to break E2EE", "run a
quoted
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5372 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../../../docs/internals/architecture/red-team-harness.md - warning
missing-refreference to a missing file: scripts/org-escrow-*.ts - warning
missing-refreference to a missing file: scripts/org-escrow-keygen.ts
Process rating: all ten parameters 49/100
- 0Tools and files. 3 referenced file(s) missing: ../../../docs/internals/architecture/red-team-harness.md, scripts/org-escrow-*.ts, scripts/org-escrow-keygen.ts
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5372 tokens
- 100Steps. 62 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 673: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 62 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.