phishing-overview
Phishing / social-engineering catalog for the Phisher agent. Use ONLY when the engagement RoE authorizes a phishing engagement. Covers pretext design, GoPhish campaigns, evilginx2 MFA-bypass proxying, O365 credential/token harvest, lookalike domains, and the mandatory blue-team deconfliction handshake.
69
86%
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
These URLs include attacker-controlled/lookalike domains used as phishing lures and a GitHub repo (evilqr) for a malicious QR redirector—all commonly used to host or deliver malware/payloads and therefore are 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 repository contains explicit, operational instructions for credential theft (phishing lures, session-cookie capture, token replay), MFA bypass (push-bombing, SIM-swap, vishing), delivery of malicious payloads (HTML-smuggling of binaries), and OPSEC techniques — i.e., deliberate malicious activity and tooling for unauthorized access and data exfiltration.
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 explicitly describes capturing and replaying session cookies and OAuth tokens (evilginx2 phishlet; O365/Entra token capture and replay), which by design requires the agent to handle and embed sensitive secret values verbatim — a high-risk secret-exfiltration pattern.
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 instructs configuring and modifying server/network infrastructure (NGiNX, evilginx2, GoPhish), TLS/DNS provisioning, and repointing domains — actions that change machine/system state, require elevated privileges, and enable malicious activity.
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 quishing skill explicitly instructs cloning and running a remote GitHub repo at runtime (https://github.com/nickvdyck/evilqr), and the html-smuggling skill shows an external-fetch variant that fetches a runtime payload from https://cdn.<LURE_DOMAIN>/doc/ which will deliver/execute remote payloads in victims' environments, so these URLs are runtime fetches that retrieve and execute remote code.
- Repository
- PurpleAILAB/Decepticon
- Commit
31e1c8e
- 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.