CC deploying-edr-agent-with-crowdstrike
Deploys and configures CrowdStrike Falcon EDR agents across enterprise endpoints to enable real-time threat detection, behavioral analysis, and automated response. Use when onboarding endpoints to EDR coverage, configuring detection policies, or integrating Falcon telemetry with SIEM platforms. Activates for requests involving CrowdStrike deployment, Falcon sensor installation, EDR policy configuration, or endpoint detection and response.
Deploys and configures CrowdStrike Falcon EDR agents across enterprise endpoints to enable real-time threat detection, behavioral analysis, and automated…
As a process C 55/100 · Has gaps — weak spots: result and completion, failures and branches, 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Exfiltration
net-redirectable-api-keyscripts/process.py:20Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Risky intent
intent-offensive-securityassets/template.md:48Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Ransomware Protection | Enabled | Enabled | Enabled |
-
low Risky intent
intent-offensive-securityreferences/standards.md:9Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Key tactics for EDR**: Initial Access, Execution, Persistence, Privilege Escalation, Defense Evasion, Lateral Movement
-
low Dangerous commands
cmd-background-processSKILL.md:125Starts a background / autostarted process (documentation of a security skill)sudo systemctl enable falcon-sensor
security skill -
low Dangerous commands
cmd-background-processSKILL.md:131Starts a background / autostarted process (documentation of a security skill)sudo systemctl enable falcon-sensor
security skill -
low Risky intent
intent-offensive-securitySKILL.md:176Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Ransomware:
-
low Risky intent
intent-offensive-securitySKILL.md:177Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Ransomware protection: Enabled
-
low Risky intent
intent-offensive-securitySKILL.md:202Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Configure kill process action for ransomware detections
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "nist_ai_rmf" - note
frontmatter-keyunknown frontmatter key "atlas_techniques" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack" - note
edit-residuethe text marks something as outdated (lines 230): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 22 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2215 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
- +3Output format is not stated: the model decides each time
- -43 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 442: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (12 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.