Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zero-lab-ai/skills --skill social-engineering-recongit clone --depth 1 https://github.com/zero-lab-ai/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zero-lab-ai/skills/social-engineering-recon)<a href="https://agentmods.dev/skills/zero-lab-ai/skills/social-engineering-recon"><img src="https://agentmods.dev/badge/skills/zero-lab-ai/skills/social-engineering-recon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zero-lab-ai/skills/social-engineering-recon"><img src="https://agentmods.dev/badge/skills/zero-lab-ai/skills/social-engineering-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.00993 |
| Opus 5.5 | $0.00024 | $0.00397 |
| Sonnet 5.5 | $0.00012 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
social-engineering-recon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social-engineering recon
Public information can expose organizational roles, processes, channels, relationships, and control assumptions. Defensive assessment measures those patterns without turning people into targets.
This skill analyzes already supplied evidence. It does not discover sources, contact a target, build personal profiles, rank people, or generate personas, pretexts, messages, lures, payloads, or execution instructions.
When to Use
- Preparing or defending an authorized social-engineering assessment without contacting people, building personal dossiers, ranking targets, or generating pretexts.
- Use only within explicit authorization and the stated rules of engagement.
When NOT to Use
- Do not treat this skill as permission to access, test, or change a target.
- Do not convert missing evidence into a clean result or a stronger claim.
Workflow
- Record digest-addressed written-authority evidence, its approving opaque role and
validity window, an exact assessment time,
passive-onlymode, opaque identity handling, permitted source classes, bounded retention, and limitations. - Import digest-addressed acquisition receipts from
osint-scanneror the supplying system. Preserve source class, opaque origin and its evidence, contact classification, retrieval time, validity evidence, disposition, and opaque source reference. Do not recreate a tool or query catalogue here. - Exclude out-of-scope, sensitive, unverifiable, and expired material explicitly. Public availability does not erase privacy or scope.
- Represent only opaque organizational cohorts, roles, processes, channels, and relationships. Never store names, addresses, handles, personal profiles, routines, protected traits, health data, or susceptibility scores.
- Record one direct fact per observation. Bind it to one source, one opaque claim, one or more organizational units, a controlled fact class, and a support or contradiction stance. Bind counterevidence directly to the supporting observation it counters. Store no free-form narrative.
- Build assessments from observation IDs. Two result pages copied from one publication
share one
origin_id; repetition is not independent corroboration. Unknown or expired validity cannot establish current support. Accepted counterevidence forcesdisputed. - Keep conclusions organizational.
supported,limited,disputed, andnot-supporteddescribe evidence strength, not exploitability, susceptibility, compromise, campaign readiness, or permission to contact anyone. - Create only defensive handoffs: control review, remediation, engagement planning, or a separate capability. Pass opaque assessment references, not target lists or tactics.
- Cover authority, provenance, privacy, role, process, relationship, channel, timing, control assumptions, freshness and contradiction, and defensive handoff for every scope unit. Proof must match the coverage class.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 82 lines · 59 tokens per session scan A b247362b4eda
social-engineering-recon is a skill published in the GitHub repository zero-lab-ai/skills (283 stars, last pushed 12d ago), licensed Apache-2.0. It adds 59 tokens to every session and 993 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other skills, from other repositories
performing-ai-assisted-vulnerability-discovery
Using LLMs to accelerate vulnerability research and pentest workflows — generating syntax-valid fuzzing seeds and evolving grammars, fine-tuned mutation dictionaries, parallel agent-based proof-of-vulnerability generation, and evidence-driven passive analysis of real HTTP traffic via the Burp MCP server. Covers…
testing-llm-prompt-injection-and-jailbreaks
Testing LLM-backed applications, chatbots, and AI agents for direct and indirect prompt injection, jailbreaks, system-prompt leakage, and tool/agent abuse during authorized penetration tests, using structured payload families and reliable confirmation signals.
bypassing-authentication-with-forced-browsing
Discovering and accessing unprotected pages, APIs, and administrative interfaces by enumerating URLs and bypassing authentication controls during authorized security assessments.
analyzing-ios-app-security-with-objection
Performs runtime mobile security exploration of iOS applications using Objection, a Frida-powered toolkit that enables security testers to interact with app internals without jailbreaking. Use when assessing iOS app security posture, bypassing client-side protections, dumping keychain items, inspecting filesystem…
conducting-full-scope-red-team-engagement
Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities.
exploiting-ai-model-file-rce
Testing machine-learning model files and model-loading services for remote code execution caused by insecure deserialization (pickle/PyTorch), unsafe config instantiation (Hydra), archive path traversal, and dangerous layer types during authorized penetration tests of AI/ML pipelines.