Design and execute a social engineering penetration test combining OSINT-driven target profiling with phishing, vishing, smishing, and physical pretexting campaigns using tools like GoPhish, the Social Engineer Toolkit (SET), and Evilginx to measure human security resilience. Use when scoping or running an authorized human-attack-surface test and reporting results to identify security awareness training gaps.
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is an openly advertised authorized social-engineering test, so its phishing and MFA-bypass content is out of scope here, but the agent scripts disable TLS certificate verification for the GoPhish API bearer token and for SMTP credentials, which weakens protections beyond what the task needs.
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.
The skill is an authorized social-engineering test playbook, and its only machine-level action is a `sudo apt install gophish` plus running GoPhish and Evilginx on a dedicated attack server, which falls under the negative example for installing well-known packages. Its physical-pentest and rogue-AP content targets employees and facilities rather than the agent's host, but the sudo install and server setup are close enough to the risk category to justify a modest score under the recall-first override.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required scripts pull campaign results from a user-supplied GoPhish server, and those results include target-submitted form data from the phishing landing pages, which external recipients can type into without the agent selecting a specific item.
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.