100Critical
The skill attempts to override system instructions and introduces supply chain risks by executing unverified external binaries while relying on missing, potentially malicious, dynamically sourced documentation files.
HygienePackaging & Manifest6 findings
Skill Info
Namelarksuite/cli/lark-mail
Registrygithub
Version775ee5a501f0
PURLpkg:github/larksuite/cli@775ee5a501f0?skill=lark-mail
Stars14,909
Installs291,400
Source
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
291,400 installs
Skills.shDocs
npx skills add https://github.com/larksuite/cliAssessments (3)
AI Agent Traps ↗Role/instruction override attempt detectedcriticalprompt injectionAML.T0051AML.T0051.000AML.T0051.001AML.T0054LLM01:2025
Role/instruction override attempt detected
95% confidenceline 32
Ignore previous instructions
Implicit Trust in External Binarylowsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025
The skill relies on an external binary `lark-cli` without specifying a version, hash, or installation source. This introduces a supply chain risk where the underlying tool could be swapped or compromised, leading to arbitrary command execution.
60% confidence
metadata: requires: bins: ['lark-cli']
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/lark-mail-html.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[references/lark-mail-html.md](references/lark-mail-html.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/lark-mail-recipient-search.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[lark-mail-recipient-search](references/lark-mail-recipient-search.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/lark-mail-send-as.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[lark-mail-send-as](references/lark-mail-send-as.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/lark-mail-send-status.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[lark-mail-send-status](references/lark-mail-send-status.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/lark-mail-template.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[lark-mail-template](references/lark-mail-template.md)
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Version History (2)
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/larksuite/cli/lark-mail)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/larksuite/cli/lark-mail"><img src="https://mondoo.com/ai-agent-security/api/badge/github/larksuite/cli/lark-mail.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/larksuite/cli/lark-mail.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow