Skills/ClawHub/soul-in-sapphire

soul-in-sapphire@2.1.3

VERIFIED· install only

Publisher claims: "Emotion-linked memory recall, self-state, subjective journal, and identity continuity." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher nextaltair · publishing for 73 daysInstalls 3,984Last detonated 7d ago
$clawhub install soul-in-sapphire
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 2026-11-07 and scored it 89/100 (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

MEDIUM
Access to sensitive file pathsscripts/memory_boundary.test.js:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv: { ...childEnv, NOTIONCTL_PATH: mock, ...env },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 actionscripts/emostate_tick.js:39 · File type combined with upload action — agent may exfiltrate local data filesmain().catch(e=>{console.log(JSON.stringify(e.details||{ok:false,stage:'input',partial:null}));console.error(e.message);process.exitCode=1;});Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathsscripts/memory_boundary.test.js:147 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst failedJournal = run('journal_write',['--journal-dbid','journal'],'{"body":"subjective fixture"}',{...env,SIS_TEST_FAIL:'1'});Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathsscripts/memory_boundary.test.js:146 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert.notEqual(run('emostate_tick',[...args.slice(0,-1),path.join(root,'failed-tick-receipt.json')],'',{...env,SIS_TEST_FAIL:'1'}).status,0);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
≈4,373 tok
1 file · 42 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.