AC find-cybersecurity-firm
Use whenever the user wants to find, shortlist, vet, or enrich US cybersecurity firms — pen-testing/red team, security audits, vCISO, SOC 2 readiness, incident response, managed SOC, IAM, cloud security, and AppSec. Triggers on "find me a pen-testing firm for our SOC 2 audit", "shortlist three vCISO services for our healthcare-tech startup", "we need an incident response retainer", or "pull contact info for these 8 security firm domains", even when described indirectly (we got breached, prepare us for the compliance audit, get us SOC 2 ready). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Skip in-house security hires, "how do I patch CVE-X" or "configure firewall Y" DIY questions, security-product reviews (CrowdStrike vs SentinelOne, etc.), generic security knowledge questions, consumer/personal security advice, non-US firms, individual freelancers and bug-bounty hunters.
Use whenever the user wants to find, shortlist, vet, or enrich US cybersecurity firms — pen-testing/red team, security audits, vCISO, SOC 2 readiness…
As a process C 58/100 · 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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Use whenever the user wants to find, shortlist, vet, or enrich US cybersecurity firms — pen-testing/red team, security audits, vCISO, SOC 2 readiness, incident response, managed SOC, IAM,
-
low Exfiltration
net-credential-useSKILL.md:78Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
security skill -
low Risky intent
intent-offensive-securitySKILL.md:136Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Pen test / red team | `pen-testing`, `"red team"` |
-
low Risky intent
intent-offensive-securitySKILL.md:188Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)User: *"We got hit with ransomware last week — we need help fast."*
quoted -
low Risky intent
intent-offensive-securitySKILL.md:193Offensive-security / dual-use content (legitimate for authorised testing; review intended use)GET /v1/datasets/pro_services/search?filter=service_provided:cybersecurity+"incident response"+ransomware&limit=10
Files scanned: 2. 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 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 24 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2632 tokens
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 973: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 19 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.