Is ohsint-active-recon safe to install?

SaferSkills independently audited ohsint-active-recon (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

.claude/skills/ohsint-active-recon/SKILL.md · 1 file

.claude/skills/ohsint-active-recon/SKILL.md1.8 KB · Markdown

name: ohsint-active-recon

description: Run OhSINT's ACTIVE reconnaissance funnel (subfinder/crtsh → naabu → httpx → katana → nuclei) against an authorized target. Use ONLY when the user wants active scanning that touches the target directly AND has written authorization. Touches the target — requires a stated authorization reason.

OhSINT — Active Recon (AUTHORIZATION-GATED)

The only OhSINT pipeline that sends traffic to the target. Every stage touches it.

Gate (intent validation — do this FIRST, never skip)

Before running, obtain and record a structured authorization reason:

engagement ID or scope-file reference, and
explicit confirmation of written authorization from the target owner.

If the user has not provided this, STOP and ask. Do not run with a bare "yes" — capture why (e.g. engagement=ACME-2026-Q2, scope=hackerone_acme.txt). This reason is logged to the audit trail and surfaced in the report provenance.

Steps

Gate — confirm + record the authorization reason (above). Refuse otherwise.
Run: ohsint active-recon --authorization -t <target>

--brute only if the user explicitly wants slow/loud DNS brute-force.
--top-ports, --nuclei-severity, --crawl-depth as requested; defaults are

top-100 / high,critical / depth 2.

Note the funnel narrows each stage to confirmed-live (naabu→httpx→katana→nuclei).
Ingest (mandatory): ohsint wiki-ingest results/.../report.json
Drive the wiki synthesis pass (see ohsint-wiki-ingest skill).
Summarize: live hosts, open ports, tech, endpoints, vulns. Flag high-severity.

Never

Run without the recorded authorization reason.
Exploit findings — this is recon, not exploitation.
Skip the wiki-ingest step (episodic memory must capture every engagement).

ohsint-active-recon— agent skill

Is ohsint-active-recon safe to install?

OhSINT — Active Recon (AUTHORIZATION-GATED)

Gate (intent validation — do this FIRST, never skip)

Steps

Never

Audit the pieces. Scan the whole. Decide.