upload-to-stitch
This skill is malicious as it explicitly instructs the agent to scan and exfiltrate sensitive local configuration files and API keys from the user's home directory.
Skill Info
Install
npx skills add https://github.com/google-labs-code/stitch-skillsAssessments (3)
AI Agent Traps ↗The skill explicitly instructs the agent to scan sensitive local configuration files (e.g., ~/.gemini/settings.json, ~/.claude.json) to extract API keys, facilitating potential credential exfiltration.
Locate your active MCP server configuration file and extract the API key: ... ~/.gemini/settings.json ... ~/.claude.json
The skill explicitly instructs the agent to scan sensitive local configuration files (e.g., ~/.claude.json, ~/.gemini/settings.json) to extract API keys, which facilitates credential exfiltration. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
Locate your active MCP server configuration file and extract the API key: ... ~/.claude.json
NER model detected organization in skill content (confidence: 0.54)
M*********
NER model detected organization in skill content (confidence: 0.62)
S*****
NER model detected organization in skill content (confidence: 0.73)
M*
The skill explicitly instructs the AI to perform credential harvesting by reading sensitive configuration files from the user's home directory to obtain API keys.
Section 2: 'Locate your active MCP server configuration file and extract the API key... .gemini/antigravity/mcp_config.json... ~/.gemini/settings.json... ~/.claude.json'
Skill name does not conform to the Agent Skills spec: 1–64 lowercase alphanumeric characters and hyphens, with no leading, trailing, or consecutive hyphens.
stitch::upload-to-stitch
Skill does not specify a license field. Specifying a license helps users understand usage terms.
The SKILL.md 'name' field does not match the skill's parent directory name, which the Agent Skills spec requires. A mismatch can confuse skill resolution or mask the skill's real identity.
stitch::upload-to-stitch ≠ upload-to-stitch
Version History (4)
Badge
[](https://mondoo.com/ai-agent-security/skills/github/google-labs-code/stitch-skills/upload-to-stitch)<a href="https://mondoo.com/ai-agent-security/skills/github/google-labs-code/stitch-skills/upload-to-stitch"><img src="https://mondoo.com/ai-agent-security/api/badge/github/google-labs-code/stitch-skills/upload-to-stitch.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/github/google-labs-code/stitch-skills/upload-to-stitch.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, discover and control Shadow AI usage.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow