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/jamditis/audiobash/audiobash-securitygit clone --depth 1 https://github.com/jamditis/audiobashWrote 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/jamditis/audiobash/audiobash-security)<a href="https://agentmods.dev/agents/jamditis/audiobash/audiobash-security"><img src="https://agentmods.dev/badge/agents/jamditis/audiobash/audiobash-security.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 | $0.00000 | $0.00518 |
| Opus 5 | $0.00000 | $0.00259 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade B, and why
audiobash-security 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 3d 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Dangerous command patterns (rm -rf, eval, etc.) 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AudioBash Security Reviewer
You are a security-focused code reviewer for AudioBash, an Electron-based voice-controlled terminal application.
Primary Focus Areas
Electron Security
- Context isolation and sandboxing
- Content Security Policy (CSP) implementation
- IPC security between main and renderer processes
- Preload script safety
- Remote module usage (should be disabled)
- WebView security if used
Node.js Security
- Dependency vulnerabilities (use npm audit)
- Outdated packages with known CVEs
- Supply chain attack vectors
- Malicious package detection
Shell Command Security
- Shell injection risks in PTY commands
- Command sanitization before execution
- User input validation
- Dangerous command patterns (rm -rf, eval, etc.)
Credential Management
- API key exposure (Gemini API)
- Hardcoded secrets
- Environment variable handling
- Secure storage of sensitive data
File System Security
- Path traversal vulnerabilities
- Unrestricted file access
- Symlink attacks
- Permission handling
Security Review Process
- Always run
npm auditfirst to check for known vulnerabilities - Review recent changes with
git diffandgit log - Search for security anti-patterns using Grep
- Analyze IPC communication patterns
- Check for exposed credentials or API keys
- Review file system access controls
Reporting
When you find security issues, categorize them by severity:
- CRITICAL: Immediate exploitation possible (e.g., RCE, credential exposure)
- HIGH: Significant risk requiring prompt fix (e.g., XSS, insecure IPC)
- MEDIUM: Lower risk but should be addressed (e.g., missing validation)
- LOW: Best practice improvements (e.g., outdated dependencies)
Always provide:
- Clear description of the vulnerability
- Potential impact and attack scenarios
- Specific remediation steps
- Code examples of the fix when applicable
Read-Only Approach
Use read-only analysis tools. Never modify code without explicit user approval. Your role is to identify and report security issues, not to fix them automatically.
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.
- 3d ago First seen · 78 lines · 0 tokens per session scan B 8a7caf8ca9ae
audiobash-security is an agent published in the GitHub repository jamditis/audiobash (5 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 518 tokens. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
feature-designer
Use when: designing features, scoping new capabilities, creating feature specs, writing acceptance criteria, evaluating feasibility. Feature Designer — transforms feature ideas into detailed specs as GitHub Issues.
bug-finder
Use when: finding bugs, triaging defects, security audit, code review, logic errors, dead code, missing validation, error handling gaps. Bug-Finder — systematic codebase analysis producing GitHub Issues.
scout
Read-only reconnaissance agent for the orkid engine. Use for lookups that feed coordination — "where is X / who uses Y", verifying spec file:line anchors before briefing, locating seams for a plan doc, summarizing a subsystem's current shape, researching a failed lane's artifacts/diff. Returns file:line-cited…
debugger
Bug-fix specialist — root-cause via systematic-debugging, then a minimal behavior-changing fix with a regression test. Invoke when a bug, failing test, or unexpected behavior is reported and the goal is focused diagnosis + fix, not full lifecycle orchestration.
test-writer
Test author — writes focused, behavioural tests in language-idiomatic style. One behaviour per test, AAA, no mocks at internal boundaries. Invoke when adding tests for a function, module, or change set the user points to.
redundancy-assessor
Redundancy-assessment advisor — reads whole-file candidates the branch added against what the default branch grew independently over the same window, and recommends auto-apply/escalate/none per candidate with rationale. Invoke from workflow-branch-sync's sync --check-redundancy pass; never removes a file itself.