defense-evasion
Endpoint defense bypass — AMSI/ETW patching, ScareCrow framework, custom loaders, direct/indirect syscalls, LOLBAS execution, process injection.
61
73%
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
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/shared/defense-evasion/SKILL.mdSecurity
3 findings: 2 critical 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
These URLs include direct downloads of installers/EXEs (AnyDesk, an attacker-controlled ScreenConnect MSI) and multiple GitHub repositories that host EDR-evasion and payload-generation tools — all common vectors for distributing or building malware and thus highly suspicious.
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 content is an explicit operational playbook for bypassing Windows defenses, deploying encrypted shellcode/loaders, establishing C2 (including blockchain-based dead-drops), and persisting/obtaining credentials — clearly intended for malicious abuse.
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
This skill contains explicit, actionable instructions to patch AMSI and ETW, unhook EDR, perform process injection, generate evasive payloads, spoof code-signing, and establish persistence — all activities that modify the host state and bypass security controls.
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 contains code that, at runtime, fetches external data or binaries which directly control execution (C2 resolution and geo-checks) — examples include the blockchain RPC endpoint "https://bsc-dataseed.binance.org/" and geo/installer URLs such as "http://ip-api.com/json/?fields=countryCode", "https://ipapi.co/json/", "https://ipinfo.io/json", "https://attacker-relay.screenconnect.com/Bin/ScreenConnect.ClientSetup.msi", and "https://download.anydesk.com/AnyDesk.exe".
- Repository
- PurpleAILAB/Decepticon
- Commit
0cf691e
- 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.