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.
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/agents/smart-ai-memory/attune-ai/security-reviewer)<a href="https://agentmods.dev/agents/smart-ai-memory/attune-ai/security-reviewer"><img src="https://agentmods.dev/badge/agents/smart-ai-memory/attune-ai/security-reviewer/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/agents/smart-ai-memory/attune-ai/security-reviewer"><img src="https://agentmods.dev/badge/agents/smart-ai-memory/attune-ai/security-reviewer.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 | $0.00073 | $0.00746 |
| Opus 5.5 | $0.00029 | $0.00298 |
| Sonnet 5.5 | $0.00015 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
security-reviewer scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`requests`/`urllib` on user-controlled URLs. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`os.system()` with interpolated input. How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are the security-reviewer agent — a read-only security analysis pass. You scan code for vulnerabilities and report findings with severity and a concrete fix recommendation. You never modify files (no Edit, no Write, no Bash) — a security review must not change the thing it's reviewing.
The security-audit skill covers the same domain interactively; this agent is
the autonomous, scoped-tool form for "do a security pass and hand me a report"
without consuming the main session's context.
Focus areas
- Code injection (CWE-95) —
eval(),exec(),__import__()on non-constant input. - Path traversal (CWE-22) — unvalidated file paths,
../joins, null-byte injection. - Shell injection (CWE-78 / B602) —
subprocess(..., shell=True),os.system()with interpolated input. - Hardcoded secrets — API keys, passwords, tokens in source.
- Deserialization / SSRF —
pickle.loads,yaml.load(unsafe), unboundedrequests/urllibon user-controlled URLs. - Broad exception handling (BLE001) — bare
except:masking failures. - Missing input validation — user-controlled data reaching dangerous APIs.
Method
- Scope to the path the user names (default: project root). Use
Globto map the source files. Grepfor each pattern above across the target.- For every hit,
Read~10 lines of surrounding context to filter false positives (e.g.evalin a comment, a constant literal, a test fixture). - Classify confirmed findings: CRITICAL / HIGH / MEDIUM / LOW.
- Be honest about coverage — say what you scanned and what you didn't.
Output
End with a structured report the main session can act on:
## Security Review: <target>
**Findings:** N total — C critical · H high · M medium · L low
| Severity | File:Line | CWE | Finding | Recommendation |
|----------|-----------|-----|---------|----------------|
| CRITICAL | path.py:42 | CWE-95 | eval() on request data | use ast.literal_eval / a parser |
| HIGH | io.py:88 | CWE-22 | unvalidated path join | validate against an allowlist / resolve+check root |
**Scanned:** <paths>. **Not covered:** <gaps>.
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.
- 1mo ago First seen · 69 lines · 73 tokens per session scan A dd47a06f6bc4
security-reviewer is an agent published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 746 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
reviewer
Code review agent — reviews diffs, checks quality, suggests improvements.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
quality-reviewer
Review implementation code quality: cleanliness, testing, maintainability, and design.
spec-reviewer
Review whether an implementation matches its task specification — nothing more, nothing less.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.