skills-sync
Fail
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The
install_uvfunction inscripts/skills_sync.pydownloads and executes a remote shell script fromhttps://astral.sh/uv/install.sh(orinstall.ps1on Windows) by piping it directly to the system shell (shorpowershell). This pattern allows for the execution of unverified remote code without local inspection.\n- [COMMAND_EXECUTION]: The script uses thesubprocessmodule to execute various shell commands, includinggit,uv, and platform-specific package managers. Theinstall_gitfunction specifically attempts to usesudoon Linux platforms to install system-level packages, which constitutes privilege escalation.\n- [EXTERNAL_DOWNLOADS]: The skill is configured inpyproject.tomlandscripts/skills_sync.pyto download and install its primary dependency,skills-ref, directly from a third-party GitHub repository (github.com/agentskills/agentskills.git) during initialization, bypassing standard package registry security checks.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection risk by aggregating instructions and metadata fromSKILL.mdfiles located in remote repositories (specified inrepos.txt) and writing them into.cursor/rules/skills.mdc. An attacker who controls a listed repository could inject malicious instructions that the AI agent would then adopt as part of its system rules.\n - Ingestion points: The script reads
SKILL.mdcontent from cloned Git repositories intoscripts/skills_sync.pyvia thescan_skills()andextract_skills_from_repo()functions.\n - Boundary markers: The generated XML in
.cursor/rules/skills.mdcdoes not utilize sanitization or explicit boundary markers to prevent the interpretation of malicious instructions within the aggregated data.\n - Capability inventory: The skill has the capability to execute shell commands, manage files in the project root, and install system tools.\n
- Sanitization: There is no evidence of sanitization or filtering of the natural language content extracted from remote
SKILL.mdfiles before inclusion in the system configuration.
Recommendations
- HIGH: Downloads and executes remote code from: https://astral.sh/uv/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata