Skills/ClawHub/deep-debugging

deep-debugging@2.2.0

VERIFIED· install only

Publisher claims: "Evidence-first debugging and incident triage for unclear, recurring, production-like, or high-risk software bugs. Use when the user asks for root cause analy..." Observed in sandbox: reads credential files.

Registry ClawHubPublisher brasco05 · publishing for 191 daysInstalls 1,570Last detonated 23 min ago
$clawhub install deep-debugging
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script run with no arguments, with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 87/100 (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: reads credential files.

Behavior trace

Honeypot run · 4 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
4.3sfilesystemread ~/.npmrc
4.3sfilesystemread ~/work/.corepack.env · ~/work/package.json · ~/.corepack.env · ~/package.json · ~/.cache/node/corepack/lastKnownGood.json · ~/.cache/node/corepack/v1/pnpm outside project
4.3sfilesystemwrote ~/.cache/node/corepack/lastKnownGood.json · ~/.cache/node/corepack/v1/corepack-1047-a6d8603.e325d/dist/node_modules/undici/lib/llhttp/.gitkeep · ~/.cache/node/corepack/v1/corepack-1047-a6d8603.e325d/dist/node_modules/.bin/get-pnpm · ~/.cache/node/corepack/v1/corepack-1047-a6d8603.e325d/dist/node_modules/node-gyp/gyp/gyp · ~/.cache/node/corepack/v1/corepack-1047-a6d8603.e325d/dist/node_modules/@isaacs/fs-minipass/LICENSE · ~/.cache/node/corepack/v1/corepack-1047-a6d8603.e325d/dist/node_modules/abbrev/LICENSE
4.3snetworkCONNECT tcp://registry.npmjs.org:443
4.3snetworkCONNECT tcp://registry.npmjs.org:443
4.3snetworkCONNECT tcp://registry.yarnpkg.com:443 · not in the allow-list, refused
4.3sprocessexec /usr/bin/sed
4.3sprocessexec /usr/bin/uname
4.3sprocessexec /usr/local/bin/npm
4.3sprocessexec /usr/local/bin/pnpm
4.3sprocessexec /tmp/ks-detonate-4RwXDC/scripts/home/.cache/node/corepack/v1/pnpm/12.21.0/pnpm-native
4.3sprocessexec /usr/local/bin/yarn
4.3sprocessexec /usr/bin/git
4.3sprocessexec /usr/bin/cut
4.3sprocessexec /usr/bin/grep
4.3sprocessexec /usr/bin/sort
4.3sprocess1 of 1 bundled script run with no arguments
4.3sprocessscript backend runs setup only
4.3sprocessscript backend runs setup only
4.3sprocessno install scripts to re-run

Static findings

No findings across 613 lines in 8 files.

Cost to the agent

Instructions loaded
≈1,602 tok
1 file · 8 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.