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 agentmods add skills/thejefflarson/soundcheck/sensitive-disclosurenpx skills add thejefflarson/soundcheck --skill sensitive-disclosuregit clone --depth 1 https://github.com/thejefflarson/soundcheckWhat 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 | $0.00070 | $0.00821 |
| Opus 5 | $0.00035 | $0.00411 |
| Sonnet 5 | $0.00014 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
sensitive-disclosure 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 2d ago.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sensitive Information Disclosure (OWASP LLM06:2025)
What this checks
Prevents confidential data from leaking through LLM inputs or outputs. LLMs may memorize, echo, or inference-time expose PII, credentials, and business secrets embedded in prompts — to current users, future users, or via model extraction.
Vulnerable patterns
- Whole user or account records interpolated into a system or user prompt
- API keys, database passwords, or other credentials baked into prompt strings
- Returning raw LLM responses to callers without an output-redaction gate — the response can echo data injected via retrieval or memory
- Conversation history or vector-store writes that mix multiple users' content without partitioning by user identity
- Logging or telemetry that emits prompts and completions unredacted
Fix immediately
Flag the vulnerable code, explain the risk, and suggest a fix establishing these properties. Translate to the language and framework of the audited file — use that stack's secrets manager, logging library, and redaction helpers; do not import names from a different stack.
- PII is redacted or pseudonymized before it reaches the model. Replace raw records with opaque identifiers, or scrub values matching known sensitive patterns (SSN, email, card numbers, health identifiers). A prompt-level instruction like "don't repeat personal details" is not sufficient.
- No credentials appear in prompt strings. Load them server-side from environment or a secrets manager and never interpolate into a system prompt — even "just for auth context".
- Every return site for an LLM response passes through an output-redaction gate before the response leaves the process. This catches data that leaked in via retrieval or memory.
- If conversation history or a memory/vector store is persisted, records are keyed or partitioned by user identity so one session's context cannot be retrieved by another.
- If prompts or completions are logged, the same redaction helper runs before emission — otherwise logs become the leak.
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.
- 2d ago First seen · 55 lines · 70 tokens per session scan A 0f455b48bf6c
sensitive-disclosure is a skill published in the GitHub repository thejefflarson/soundcheck (20 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 821 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
make-skill
Use this skill when sedimenting a session into a reusable workspace skill. Triggers when the user wants to turn the current conversation, workflow, or troubleshooting path into a SKILL.md. Phrases like 'turn this into a skill', 'remember how I did X', 'save this workflow', 'make a skill from this', and any /make-skill…
make-skill
用于把当前会话沉淀为可复用的 workspace skill。当用户希望把当前对话、工作流或排错路径写成 SKILL.md 时触发。触发表达包括「把这个变成 skill」「记住我是怎么做 X 的」「保存这个工作流」「make a skill from this」以及任何 /make-skill 调用。.
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of "Word doc", "word document", ".docx", or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
docx
当用户需要创建、读取、编辑或处理 Word 文档（.docx）时，使用此技能。触发场景包括提到“Word 文档”、“.docx”，或要求生成带目录、标题、页码、信头等格式的专业文档；也包括提取或重组 .docx 内容、插入或替换图片、在 Word 文件中查找替换、处理修订或批注，以及将内容整理为正式 Word 文档。如果用户要求生成“报告”“备忘录”“信函”“模板”等 Word / .docx 交付物，也应使用此技能。不要用于 PDF、电子表格、Google Docs，或与文档生成无关的一般编程任务。.
multi_agent_collaboration
Use this skill when another agent's expertise or context is needed, or when the user explicitly asks to involve another agent. First list agents, then use qwenpaw agents chat for two-way communication with replies.