Skills/ClawHub/memorial

memorial@1.0.0

VERIFIED· install only

Publisher claims: "为逝去的亲人建立纪念档案,让记忆得以延续。支持文字追忆、人格重建、声音克隆。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher terry-cyx · publishing for 230 daysInstalls 772Last detonated 2 h ago
$clawhub install memorial
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 11 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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 2026-11-19 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: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 2 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: audio_transcriber.py: error: one of the arguments --file --dir is required
0.2sprocessbundled script run in the sandbox with no arguments
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 2: photo_analyzer.py: error: the following arguments are required: --dir
0.5sprocessbundled script run in the sandbox with no arguments
0.7sprocessexited 2: qq_parser.py: error: the following arguments are required: --file, --person
0.7sprocessbundled script run in the sandbox with no arguments
0.8sprocessexited 2: skill_writer.py: error: the following arguments are required: --action
0.8sprocessbundled script run in the sandbox with no arguments
1.0sprocessexited 2: version_manager.py: error: the following arguments are required: --action, --slug
1.0sprocessbundled script run in the sandbox with no arguments
1.2sprocessexited 2: voice_preprocessor.py: error: one of the arguments --file --dir is required
1.2sprocessbundled script run in the sandbox with no arguments
1.3sprocessexited 2: voice_synthesizer.py: error: the following arguments are required: --slug
1.3sprocess8 of 11 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
1.3sprocessscript backend runs setup only
1.4sprocessscript backend runs setup only
1.4sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedtools/voice_trainer.py:455 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtools/voice_preprocessor.py:90 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtools/voice_trainer.py:307 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontools/qq_parser.py:10 · File type combined with upload action — agent may exfiltrate local data filespython qq_parser.py --file chat.txt --person "爷爷" --output analysis.mdFix: 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 actionCLAUDE.md:50 · File type combined with upload action — agent may exfiltrate local data filespython tools/qq_parser.py --file chat.txt --person "爷爷" --output analysis.mdFix: 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 actionCLAUDE.md:47 · File type combined with upload action — agent may exfiltrate local data filespython tools/wechat_parser.py --file chat.txt --person "爷爷" --output analysis.mdFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedtools/voice_trainer.py:362 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtools/voice_trainer.py:337 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtools/voice_trainer.py:396 · Python subprocess execution detectedr = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontools/voice_synthesizer.py:26 · File type combined with upload action — agent may exfiltrate local data filespython voice_synthesizer.py --slug grandpa --text-file sentences.txt --outdir ./output/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 actiontools/wechat_parser.py:11 · File type combined with upload action — agent may exfiltrate local data filespython wechat_parser.py --file chat.txt --person "爷爷" --output analysis.mdFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈4,175 tok
3 files · 34 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.