Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Paper Summarize Pdf To Feishu
v2.0.0总结论文 PDF 为飞书文档（含图表）。采用主控 - 子代理 (Orchestrator-Subagents) 架构处理长流程。 支持学术论文、技术报告的自动去重、总结、配图、真实比对审核与人工确认。 触发场景：发送 PDF 附件、"总结这个 PDF"、"把 PDF 写成飞书文档"、"论文总结"。
⭐ 1· 72·0 current·0 all-time
by@yy-fan
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name/description (summarize PDF → Feishu doc) align with the included scripts (metadata extraction, text extraction, figure locating, supplement merging, duplicate checking). However, the skill references Feishu document tokens and feishu_doc actions but declares no Feishu credentials or primary env var — a capability gap. It also expects workspace variables (e.g., $PAPER_DIR, $PAPERS_DIR) that are not declared in requires.env or documented as required configuration.
Instruction Scope
SKILL.md instructs the agent to traverse/scan a PAPERS_DIR, read/write many files under $PAPER_DIR, spawn subagents (sessions_spawn), and use feishu_doc actions. Scripts will look for feishu_doc_token.txt in paper directories and may construct Feishu URLs. The instructions reference environment variables and paths that are not declared, giving the agent broad discretion over filesystem locations; that increases risk of unintended access or disclosure if the variables point to wide-ranging directories.
Install Mechanism
There is no remote download/install of arbitrary code; required binaries (poppler tools, tesseract, jq) are standard and the SKILL.md even suggests apt packages. All logic is in bundled shell scripts. No suspicious external URLs or archive extraction are used.
Credentials
The skill claims no required env vars, yet expects/uses $PAPER_DIR and $PAPERS_DIR and reads feishu_doc_token.txt files if present. It references Feishu document tokens and instructs actions that require Feishu authentication, but does not declare or request Feishu API keys/tokens (nor specify where to securely provide them). This mismatch is disproportionate and ambiguous — the skill will need Feishu credentials to publish, and may instead look for token files on disk.
Persistence & Privilege
always:false and no evidence the skill modifies other skills or system-wide agent settings. It writes logs and output into a per-paper workspace as described; that is expected for this workflow. Still, because the script scans PAPERS_DIR, the effective privilege depends on what directory is supplied.
What to consider before installing
This skill mostly does what it says (extract text, OCR figures, build summaries, check duplicates) and all logic is in included shell scripts — that's good. However, before installing or running: 1) Confirm how Feishu publishing is authenticated: the skill references feishu_doc actions and feishu_doc_token.txt but declares no Feishu credential; do not place API tokens in global or shared directories. 2) Define and lock down $PAPER_DIR and $PAPERS_DIR to a dedicated sandbox/workspace so the scripts cannot traverse your entire papers directory or other sensitive folders. 3) Expect the agent to spawn subagents and write logs; review the logs and output location. 4) If you want to publish to Feishu, require the maintainer to declare a clear primaryEnv (e.g., FEISHU_API_TOKEN) and document where/how tokens are supplied. 5) If you cannot verify how feishu_doc actions are executed (what service/tool actually performs network requests), run the skill offline or in a sandbox first and inspect produced commands and any network calls. If these issues are not clarified, treat the skill as risky for production use.Like a lobster shell, security has layers — review code before you run it.
latestvk978c9mznyj2esek2fw9vy95z5844dhq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
📄 Clawdis
Binspdftotext, pdfinfo, pdfimages, pdftoppm, tesseract, jq