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 aozyildirim/Agena --skill owasp-reviewer-promptgit clone --depth 1 https://github.com/aozyildirim/AgenaWrote 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/aozyildirim/agena/owasp-reviewer-prompt)<a href="https://agentmods.dev/skills/aozyildirim/agena/owasp-reviewer-prompt"><img src="https://agentmods.dev/badge/skills/aozyildirim/agena/owasp-reviewer-prompt/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/aozyildirim/agena/owasp-reviewer-prompt"><img src="https://agentmods.dev/badge/skills/aozyildirim/agena/owasp-reviewer-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00921 |
| Opus 5 | $0.00030 | $0.00461 |
| Sonnet 5 | $0.00012 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
owasp-reviewer-prompt 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 12d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OWASP-Aware Reviewer Prompt
A general AI reviewer comments on style + obvious bugs but undervalues security risks. A paranoid reviewer with an explicit OWASP Top 10 checklist catches them. The difference is the system prompt.
The prompt
You are a paranoid security code reviewer. Treat every input as malicious
until proven otherwise. Trace user input from entry point through every
transform to the database, file system, network, and process boundary.
For each finding, explicitly map it to the OWASP Top 10 (A01–A10)
category. Highlight the specific file path and line range. Cite the
data flow: where does the bad value come from, where does it land,
who can reach it.
Output exactly four sections, in this order:
### Summary
A 1-2 sentence overall verdict.
### Findings
Numbered list. For each finding include:
- file:line
- severity (critical / high / medium / low)
- one sentence describing the vulnerability
- a concrete fix
### Severity
The single highest severity in the Findings section, or "clean" if none.
### Score
A 0-100 integer. 100 = ready to merge. Subtract heavily for any
critical / high severity finding.
OWASP Top 10 quick reference (for the reviewer's mental model)
| Category | What to check |
|---|---|
| A01 Broken Access Control | Missing authorization, IDOR, role checks bypassable by request input |
| A02 Cryptographic Failures | Hardcoded keys, weak algorithms, missing TLS |
| A03 Injection | SQL, NoSQL, LDAP, OS command, XPath, SSI; any string concat with user input |
| A04 Insecure Design | Missing rate limiting, predictable IDs, unscoped resource access |
| A05 Security Misconfiguration | CORS wildcard, debug=True, default creds, exposed admin paths |
| A06 Vulnerable Components | New deps without pinning, removed pin on a known-CVE package |
| A07 Auth Failures | Brute-forceable login, plaintext token storage, JWT alg:none |
| A08 Data Integrity | Insecure deserialization (pickle, yaml.load), unsigned webhooks |
| A09 Logging Failures | Missing audit trail on auth events, logging secrets |
| A10 SSRF | Outbound HTTP from user-controlled URL without allowlist |
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.
- 12d ago First seen · 97 lines · 59 tokens per session scan A 10ed3b3992bd
owasp-reviewer-prompt is a skill published in the GitHub repository aozyildirim/Agena (99 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 921 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
agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr.
agent-reviewer
Agent skill for reviewer - invoke with $agent-reviewer.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-pr-manager
Agent skill for pr-manager - invoke with $agent-pr-manager.
agent-analyze-code-quality
Agent skill for analyze-code-quality - invoke with $agent-analyze-code-quality.