Extracts Feishu/Lark Docs, Wiki, Sheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API, no LLM paraphrasing, browser-DOM fallback when lark-cli can't reach content. Use whenever the source is a Feishu/Lark URL and fidelity matters, 导出飞书文档/合集/妙记转写, 把飞书 wiki 转 markdown, or archiving a collection, even if the user just says "save this". Also covers owner-exported .docx → Markdown.
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 27 findings, highest severity high.
- Highest severity
- high
- Findings
- 27
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked yesterday
Result
High risk Waxell rates it high risk: 27 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (27)
high · 15
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:142 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:162 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:244 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:246 · skillspector:AE1
- high
Memory Poisoning: Memory Manipulation
references/original-media-and-reader.md:56 · skillspector:MP3
- high
Data Exfiltration: Env Variable Harvesting
scripts/archive_attachments.py:242 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
scripts/capture_table.py:45 · skillspector:E2
- high
YARA Match: YARA rule 'info_stealer': Information stealer patterns (credential harvesting, browser data theft) [malware]
scripts/download_feishu_images.py:200 · skillspector:YR1
- high
YARA Match: YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas
scripts/feishu_dom_capture.js:53 · skillspector:YR4
- high
Privilege Escalation: Credential Access
scripts/feishu_extract_refs.py:258 · skillspector:PE3
- high
Data Exfiltration: Env Variable Harvesting
scripts/fetch_comments.py:29 · skillspector:E2
- high
YARA Match: YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas
scripts/restore_docx_headings.py:54 · skillspector:YR4
- high
Tells Claude to install unpinned packages (browser_cookie3, requests)
scripts/download_feishu_images.py:9 · skill_risk:S2
- high
Tells Claude to install unpinned packages (browser_cookie3, requests, file=sys.stderr)
scripts/download_feishu_images.py:43 · skill_risk:S2
- high
Tells Claude to install unpinned packages (python-docx)
scripts/restore_docx_headings.py:44 · skill_risk:S2
medium · 12
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Rogue Agent: Session Persistence
references/permission-and-failure-boundaries.md:40 · skillspector:RA2
- medium
Dangerous Code Execution: subprocess module call
scripts/archive_attachments.py:279 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'markdown' from pathlib.Path.read_text (line 105, file read) → pathlib.Path.write_text (file wr
scripts/build_feishu_markdown.py:109 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
scripts/capture_table.py:55 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/check_reader_delivery.py:78 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/download_original_preview.py:88 · skillspector:AST4
- medium
Excessive Agency: Autonomous Decision Making
scripts/download_original_preview.py:124 · skillspector:EA2
- medium
Dangerous Code Execution: subprocess module call
scripts/fetch_comments.py:33 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/render_api_capture.py:147 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_documented_body_recipes.py:61 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_feishu_extract_refs.py:242 · skillspector:AST4
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-167 added, 13 changed High riskgot riskier
- v12026-11-03 Review findings
Files
Files
41 files, 436 KB in total. Names only; open them on GitHub.
- SKILL.md
- references/archive-destination-handoff.md
- references/archive-storage-contract.md
- references/attachment-archives.md
- references/browser-dom-fallback.md
- references/browser-failure-rules.md
- references/capture-manifest.md
- references/comments-and-feedback.md
- references/docx-export-to-markdown.md
- references/external-video-resources.md
- references/feishu-minutes-transcript.md
- references/lark-cli-api-extraction.md
- references/original-media-and-reader.md
- references/permission-and-failure-boundaries.md
- references/table-capture.md
- scripts/archive_attachments.py
- scripts/build_feishu_markdown.py
- scripts/build_manual_catalog.py
- scripts/capture_table.py
- scripts/check_archive_storage.py
- scripts/check_heading_coverage.py
- scripts/check_reader_delivery.py
- scripts/download_feishu_images.py
- scripts/download_original_preview.py
- scripts/feishu_dom_capture.js
- scripts/feishu_extract_refs.py
- scripts/fetch_comments.py
- scripts/lark_result.py
- scripts/render_api_capture.py
- scripts/restore_docx_headings.py
- tests/fixtures/source-cards.html
- tests/test_archive_storage.py
- tests/test_attachment_archives.py
- tests/test_build_manual_catalog.py
- tests/test_capture_table.py
- tests/test_comments.py
- tests/test_documented_body_recipes.py
- tests/test_feishu_extract_refs.py
- tests/test_lark_result.py
- tests/test_original_media.py
- tests/test_reader_delivery.py
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
ghostty-usedaymadeSnapshots local Codex/Claude CLI sessions across terminals and restores IDs in Ghostty after reboot (保存会话/重启前备份/恢复窗口), audits survivors,… High riskEngineeringAI & agents1.5k
git-safety-netdaymadeAudits, preserves and recovers local Git state before cleanup: unpushed or wrong-branch commits, dirty worktrees, duplicate clones,… High riskEngineeringAI & agents1.5k
github-opsdaymadeOperates GitHub via gh CLI and REST/GraphQL: PRs, issues, Actions, self-hosted Runner inventory/capacity, repos, collaborators, org… High riskEngineeringDesign1.5k
lark-cli-routerdaymadeRoutes any Feishu/Lark/Doubao operation, including recording lookup by date (按日期找会议录音), through the version-matched lark-cli domain guide… High riskEngineeringProductivity1.5k