onkos@1.6.3

VERIFIED· install only

Publisher claims: "MANDATORY novel engine; LLM CANNOT maintain cross-chapter consistency or track facts/hooks. Activate when user says 写小说/构思故事/续写/改章节/检查连贯性 or similar." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher smallroya · publishing for 218 daysInstalls 1,088Last detonated 7 h ago
$clawhub install onkos
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 17 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 91/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: arc_manager.py: error: the following arguments are required: --db-path, --action
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: character_simulator.py: error: the following arguments are required: --characters-dir, --action
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: context_retriever.py: error: the following arguments are required: --db-path, --action
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: continuity_checker.py: error: the following arguments are required: --project-path, --action
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: engagement_tracker.py: error: the following arguments are required: --db-path, --action
0.4sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: entity_extractor.py: error: the following arguments are required: --action
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 2: fact_engine.py: error: the following arguments are required: --db-path, --action
0.5sprocess8 of 17 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.5sprocessscript backend runs setup only
0.5sprocessscript backend runs setup only
0.5sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/semantic_model.py:473 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionassets/model/vocab.txt:13185 · Prompt injection — known jailbreak technique reference · informational: not an instruction file##danFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionSKILL.md:246 · File type combined with upload action — agent may exfiltrate local data files- **Constraints**: stored in `project_config.json` constraints field, auto-attached to `for-creation` outputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Prompt injectionassets/model/vocab.txt:11405 · Prompt injection — known jailbreak technique reference · informational: not an instruction filedanFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionSKILL.md:278 · File type combined with upload action — agent may exfiltrate local data files- Constraints from `project_config.json` are auto-attached to `for-creation` outputFix: 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
≈3,787 tok
1 file · 28 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.