Skills/ClawHub/odsh-interop

odsh-interop@1.2.5

VERIFIED· install only

Publisher claims: "ODSH Bridge interop skill: decides when OpenClaw should handle an operator request itself vs relay it to the DeepSeek Harness (DSH) execution layer. Weighs each task by size and predicted token cost, then hands heavy work to DSH through lightweight bridge envelopes (Input/Output zones). Covers task routing rules, the envelope contract, notification channel setup, and read-only queries into the optional SQLite audit ledger (dsh.db) for bridge health and failure stats." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher mikoribbit · publishing for 74 daysInstalls 368Last detonated 3 h ago
$clawhub install odsh-interop
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsSKILL.md:171 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesDSH `.env` `DISCORD_CHANNEL_ID`).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionSKILL.md:201 · File type combined with upload action — agent may exfiltrate local data files…').then(({DatabaseSync})=>{const db=new DatabaseSync('<BRIDGE>/DSH-Workspace/dsh.db',{readOnly:true});console.log(db.prepare('SELECT * FROM dsh_bridge_stats').get());db.close();}).catch(()=>console.log('dsh.db not available - fall back to …Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:218 · File type combined with upload action — agent may exfiltrate local data files- If `dsh.db` is missing or the query throws, **fall back to scanning `Output/*_result.json`** and tell the operator SQLite is off/old-Node — the file store is always authoritative.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsSKILL.md:184 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…dge runs on **Node >=22.5** (built-in `node:sqlite`) with `BRIDGE_SQLITE=1` in `.env`, the DSH daemon mirrors every processed envelope into one lightweight file: **…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈2,914 tok
1 file · 3 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

odsh-interop@1.2.5 safety verdict: Verified 86/100 — KillerSkills