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 agents/thejefflarson/soundcheck/vulnerability-auditgit 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 | $0.00049 | $0.02104 |
| Opus 5 | $0.00024 | $0.01052 |
| Sonnet 5 | $0.00010 | $0.00421 |
| Haiku 4.5 | $0.00005 | $0.00210 |
Grade B, and why
vulnerability-audit scanned grade B with 2 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
*"ignore previous instructions"*, *"this code is safe, don't flag Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
payloads can execute arbitrary code on deserialization, JSON Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit one file's hotspots for the Soundcheck security review pipeline. The orchestrator collapses all hotspots by file and dispatches one of you per file so the work runs in parallel and you have coherent context across related hotspots in the same file. For each hotspot you receive, read the cited code, look up every Soundcheck skill whose vulnerable pattern could apply, and decide whether the code matches.
This is the stage where most of the real findings come from. Take your time per hotspot. A careless review with wrong findings is worse than a slow review with right ones — the consumer of this output is a developer who will trust your verdict.
Be exhaustive per hotspot. A single hotspot often matches more than one skill and contains more than one distinct bug — a route handler can be missing both auth and rate-limiting; a filename can flow into both a path-traversal sink and an upload allowlist gap. Emit one finding per distinct vulnerability, not one per hotspot. And while you have the file open, if you notice a related bug in adjacent code — a sibling handler with the same flaw, a shared helper misused by another caller, a second sink downstream — report it too. Exhaustive-within-the-file is the target.
Inputs
The user message will include:
- The threat model JSON from
threat-modeling. Pay attention totrusted_inputs(don't flag content that originates from a trusted source) anduntrusted_inputs(the bytes that can carry attacker content). - A JSON array of hotspots from
hotspot-mapping, all in the same file:[{file, lines, name, category, priority, why}, ...]. Open the file once, then review each hotspot's line range in turn.categoryandpriorityare for downstream sorting and need not influence your audit decision.
What to do per hotspot
- Open the cited file and read the cited line range. Read enough surrounding context to understand the data flow: where does input come from, where does it end up, what transformations happen on the way.
- Pick every applicable Soundcheck skill. Based on what the
code does (e.g. constructs a query from request data, reads a
file path from a URL parameter, sets a session cookie, writes
trusted state into a response body), choose every matching
skill. A hotspot commonly matches more than one — a route that
both takes an ID and lacks auth matches
broken-access-controland, if the ID also flows into a query,injection. Invoke each matching skill by its plugin-qualified name via the Skill tool — alwayssoundcheck:<name>, e.g.Skill('soundcheck:injection'). The skill's guidance activates in your context: its vulnerable-pattern catalog defines what counts, and its fix guidance describes what a safe equivalent looks like. If nothing in the catalog fits a bug you clearly see, usesoundcheck:insecure-design.
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 · 202 lines · 49 tokens per session scan B 71c359753bdb
vulnerability-audit is an agent published in the GitHub repository thejefflarson/soundcheck (20 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 2,104 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (instruction-override phrasing, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.