idac: IDA Pro command line tool for agents and humans

by trailofbits · Agent Tool · ★ 56

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install idac

git clone https://github.com/trailofbits/idac.git
uv tool install .            # installs the `idac` command on your PATH

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 67/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars56
Forks5
LanguagePython
CategoryAgent Tool
LicenseApache-2.0
Quality Score67/100
Open Issues4
Last Updated2026-10-02
Created2026-04-22
Platformspython
Est. Tokens~16k

About idac

idac The IDA Pro CLI built for agents and humans. One Unix socket — no JSON-RPC framing, no sidecar daemon, no MCP server. Just from any shell or agent. is in early alpha and actively developed. It is already useful day to day, but the CLI surface may still change between releases.

Compatible Skills

These tools work well together with idac for enhanced workflows:

  • IDAssistMCP — semantic(0.45)+complementary+same_lang+similar_pop+shared_platform (66%)
  • ida-agent-bridge — semantic(0.43)+complementary+same_lang+similar_pop+shared_platform (60%)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools