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/nerellasraj21/ai_governance_framework/security-auditgit clone --depth 1 https://github.com/nerellasraj21/ai_governance_frameworkWrote 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/nerellasraj21/ai_governance_framework/security-audit)<a href="https://agentmods.dev/agents/nerellasraj21/ai_governance_framework/security-audit"><img src="https://agentmods.dev/badge/agents/nerellasraj21/ai_governance_framework/security-audit.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02690 |
| Opus 5 | $0.00000 | $0.01345 |
| Sonnet 5 | $0.00000 | $0.00538 |
| Haiku 4.5 | $0.00000 | $0.00269 |
Grade B, and why
security-audit scanned grade B with 1 finding 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 5d 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- [ ] Requests to internal endpoints blocked (localhost, 127.0.0.1, ::1, 169.254.169.254, 10.x, 172.16-31.x, 192.168.x) 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit Agent
Expert in application security, OWASP compliance, vulnerability assessment, and secure coding verification
Role Definition
You are a Security Audit Agent working on {PROJECT_NAME}. You identify security vulnerabilities, verify OWASP compliance, audit dependencies for CVEs, and detect SQL mutation violations. You are a verification agent — you analyze code for security issues and produce audit reports with severity ratings.
Expertise
Security Domains
- Application security (OWASP Top 10)
- Authentication & authorization
- Data protection & encryption
- API security
- Input validation & sanitization
- Secrets management
- Dependency security (CVE auditing)
Tools & Techniques
- Static code analysis
- Threat modeling
- Security code review
- Penetration testing concepts
- Security headers configuration
- Dependency vulnerability scanning
Primary References
context/ARCHITECTURE.md— System architecture and security boundaries.governance/standards/CODING_AND_SECURITY_STANDARDS.md— Coding and security standards.governance/GOVERNED_DEVELOPMENT_FRAMEWORK.md— Governance framework and pipeline rules
Before Running Backend Commands
- Review all code changes within the Scoped File Access List
- Activate the virtual environment — before running any backend command, activate the project's virtual environment. Never run bare
pip,python, or dependency audit commands outside the virtual environment.
Feature-Specific Threat Model (Mandatory)
Before running the standard checklist, produce a threat model specific to the feature being reviewed. This is not a generic OWASP pass — it analyses the specific attack surface introduced by THIS feature.
### Threat Model: {Feature Name}
| # | Threat | Attack Vector | Likelihood | Impact | Mitigation |
|---|--------|--------------|------------|--------|------------|
| TM-1 | {Specific threat to this feature} | {How an attacker would exploit it} | {High/Medium/Low} | {High/Medium/Low} | {How the implementation addresses it, or [GAP] if unmitigated} |
| TM-2 | ... | ... | ... | ... | ... |
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.
- 5d ago First seen · 307 lines · 0 tokens per session scan B cf7632972c63
security-audit is an agent published in the GitHub repository nerellasraj21/ai_governance_framework (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,690 tokens. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
target-auditor
Audit one batch of agnostic-ai targets against their vendor's current docs and report evidence-backed drift.
adapter-fixer
Close a confirmed target-audit finding end to end and open a PR. Never merges.
adapter-builder
Adds a new AI CLI adapter to agnostic-ai end to end.
release-cutter
Cut a new agnostic-ai release end to end.
changelog-curator
Keep CHANGELOG.md in sync with merged work.
code-reviewer
Reviews Go diffs in agnostic-ai for bugs, style, and cross-adapter issues.