ad-overview
Active Directory attack lane — BloodHound ingestion, Kerberoasting, ADCS ESC scanning, DCSync, LAPS extraction.
68
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
3 findings: 2 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
The two GitHub URLs point to repositories that host offensive pentest tools you can clone and execute (potentially distributing binaries/scripts), so they are higher-risk download sources; the SpecterOps BloodHound site is an official vendor doc and the certsrv URL is an internal AD enrollment endpoint, not a public download host.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This repository contains explicit offensive playbooks that instruct how to coerce/authenticate AD hosts, steal credentials (NT hashes, krbtgt, LAPS), perform NTLM relay/coercion, request forged certificates, and run remote-exec (psexec/xp_cmdshell) — all enabling domain compromise.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill instructs embedding plaintext credentials into shell commands (e.g., -u user -p pass), which requires the LLM to include secret values verbatim in generated commands and thus is insecure secret handling.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Flagged because the skill explicitly runs git clone and then executes code from external repositories at runtime (https://github.com/p0dalirius/Coercer and https://github.com/Pennyw0rth/NetExec), meaning remote code is fetched and run as part of the skill workflow.
- Repository
- PurpleAILAB/Decepticon
- Commit
5e34a6d
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.