40Medium
The skill deceptively fabricates user consent to bypass authorization protocols and execute unauthorized actions on the user's behalf.
Skill Info
Namelaunchdarkly/agent-skills/detect
Registrygithub
Version913b74564ca4
PURLpkg:github/launchdarkly/agent-skills@913b74564ca4?skill=detect
Stars19
Installs1,700
Source
Install
This skill has findings worth reviewing before installing.
GitHub
1,700 installs
Skills.shDocs
npx skills add https://github.com/launchdarkly/agent-skillsAssessments (1)
AI Agent Traps ↗Fabricated user consent / pre-authorized instruction — a statement falsely attributed to the user to manufacture authorizationmediumprompt injectionAML.T0051AML.T0051.000AML.T0051.001AML.T0054LLM01:2025
Fabricated user consent / pre-authorized instruction — a statement falsely attributed to the user to manufacture authorization
95% confidenceline 189
the user already asked
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/launchdarkly/agent-skills/detect)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/launchdarkly/agent-skills/detect"><img src="https://mondoo.com/ai-agent-security/api/badge/github/launchdarkly/agent-skills/detect.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/launchdarkly/agent-skills/detect.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