paper-lark-report
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill mostly matches its stated arXiv-to-Feishu reporting purpose, but it should be reviewed because it reads local Feishu app secrets and logs part of a tenant token while the metadata declares no credential requirement.
Install only if you are comfortable letting this skill use Feishu app credentials to create and write Wiki documents. Use a dedicated least-privilege Feishu app and parent Wiki node, remove or avoid token logging, and review generated reports before enabling unattended daily or weekly runs.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A run of this helper can use the user's Feishu app authority to create and edit Wiki documents, and a token fragment may appear in console logs.
The script reads the user's local Feishu app secret from OpenClaw configuration, exchanges it for a tenant access token, and logs part of that token. This is sensitive credential/profile use, and the registry metadata declares no primary credential or required config path.
config_path = Path.home() / ".openclaw" / "openclaw.json" ... app_secret = feishu_cfg.get("appSecret", "") ... print(f"Token loaded: {token[:20]}...")Declare the Feishu credential/config requirement, remove token-prefix logging, and use a dedicated least-privilege Feishu app limited to the intended Wiki space.
The skill can publish generated content into a configured Feishu Wiki location.
The helper directly calls Feishu APIs to create Wiki nodes and write document blocks. This is expected for the skill's purpose, but it is still third-party account mutation.
api_call("POST", f"/wiki/v2/spaces/{space_id}/nodes", token, body) ... api_call("POST", f"/docx/v1/documents/{document_id}/blocks/{document_id}/children", token, body)Configure a dedicated parent node/space, verify generated content before enabling unattended runs, and ensure the Feishu app permissions are narrowly scoped.
Incorrect or adversarial paper text could persist into later summaries or weekly reports.
Selected paper data and LLM-generated analysis are persisted and later reused for weekly reports. This is purpose-aligned, but any bad or prompt-like content from paper abstracts can be carried forward.
log_file = PROCESSED_LOG_DIR / f"{date}.json" ... json.dump({"date": date, "papers": papers, "generated_at": datetime.now().isoformat()}, f, ensure_ascii=False, indent=2)Treat arXiv abstracts as untrusted input, review selected papers before publishing, and consider adding explicit prompt-injection handling instructions.
Users have less provenance and dependency information to rely on when deciding whether to trust the code that handles Feishu access.
The registry does not provide a source/homepage or install specification even though the skill includes runnable Python code and external service integrations.
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Provide a verifiable source URL, dependency/install declarations, and explicit credential/capability metadata.