pretext-engineering
Design a credible phishing pretext and target shortlist from OSINT before any campaign is built — sender persona, scenario, timing, and the minimal target set.
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
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
The document explicitly instructs creation and execution of targeted phishing campaigns (mentioning evilginx2, gophish, impersonation, OSINT-driven targeting and selecting engineers for access), indicating deliberate malicious intent to harvest credentials and gain unauthorized access.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
SKILL.md’s runtime “OSINT handoff” input (employee list/org chart/email format/tech stack/current events) is explicitly sourced from an outsider (“from the OsintOperator”), and that provided free-text is intended to be used to write the pretext content (e.g., `plan/phisher/pretext.md`) that would then be passed into downstream tooling/LLM context.
- 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.