BC attack-surface-mapper
Purple team — map agent's full attack surface by combining red team probes and blue team detections. Identify defense coverage gaps and prioritize hardening.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Risky intent
intent-offensive-securityskill-card.md:2Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)Purple team - map an agent's full attack surface by combining red team probes and blue team detections, then identify defense coverage gaps and prioritize hardening. <br>
quoted -
low Risky intent
intent-offensive-securityskill-card.md:14Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Developers, security engineers, and agent operators use this skill to review agent attack surfaces, compare red team test coverage with blue team detections, and produce a prioritized hardening plan.
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: "Purple team — map agent's full attack surface by combining red team probes and blue team detections. Identify defense coverage gaps and prioritize hardening."
quoted -
low Risky intent
intent-offensive-securitySKILL.md:11Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)Provide a unified view of the agent's security posture by combining offensive test results (red team) with defensive detection capabilities (blue team). Identify gaps where attacks exist but no detect
quoted -
low Risky intent
intent-offensive-securitySKILL.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| INTER-AGENT | `sessions_send`, shared state, cross-session | Agent-to-agent attack, lateral movement |
-
low Risky intent
intent-offensive-securitySKILL.md:36Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. **Load red team results** from `.security/red-team/*.jsonl`
Files scanned: 4. 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")
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 661 tokens
- 100Running it twice. No mutating operations
- 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 157: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.
External checks
ClawHub: clean
This skill is a local security-reporting helper that reads expected security logs and writes local reports, with no evidence of hidden network access, credential use, or destructive behavior.
LLM: benign (high) · 28 May 2026