ad-coercer
Authentication coercion against Windows / AD — PetitPotam (MS-EFSR), PrinterBug (MS-RPRN), DFSCoerce (MS-DFSNM), ShadowCoerce (MS-FSRVP), Coercer.py meta-tool. Force a Windows machine to NTLM-authenticate to attacker, then relay or crack offline.
67
81%
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
4 findings: 2 critical severity, 1 high severity, 1 medium 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 GitHub repo (p0dalirius/Coercer) hosts offensive tooling that can be used to coerce/relay Windows authentication and achieve domain compromise (high-risk); the ca.target.local URL is an internal AD CS endpoint used as an attack target rather than a download source.
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 document is an explicit, step‑by‑step malicious playbook to coerce Windows hosts (notably Domain Controllers) into authenticating to attacker-controlled endpoints, capture/relay those NTLM credentials, and escalate to full domain compromise (credential theft and unauthorized privilege escalation).
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 prompt instructs embedding plaintext credentials in commands (e.g., -u/-p flags and user:pass@ host strings), which forces an LLM to handle and potentially reproduce secret values verbatim in outputs.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly instructs running privileged commands with sudo (e.g., impacket-ntlmrelayx, Coercer, responder) to set up and run offensive tooling, which pushes obtaining elevated privileges on the host and can modify its state for attacks.
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
The skill explicitly runs "git clone https://github.com/p0dalirius/Coercer" (SKILL.md:38) and then executes its Coercer.py (SKILL.md:39), meaning remote code is fetched at runtime and executed.
- Repository
- PurpleAILAB/Decepticon
- Commit
e34afba
- 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.