skills/akillness/jeo-skills/devup-ui/Gen Agent Trust Hub

devup-ui

Fail

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The helper script scripts/install.sh contains a shell command injection vulnerability in the install_skill function. The script iterates over the AGENTS environment variable and appends its values unquoted to a variable AGENT_FLAGS, which is then executed unquoted inside an npx command: npx skills add "$REPO_URL" --skill "$SKILL" $GLOBAL_FLAG $AGENT_FLAGS. This allows for arbitrary command execution if shell metacharacters (e.g., semicolons, backticks, or command substitutions) are present in the AGENTS input.\n- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of several Node.js packages under the @devup-ui scope (e.g., @devup-ui/react, @devup-ui/next-plugin) through standard package managers. These are external dependencies required for the library's functionality.\n- [REMOTE_CODE_EXECUTION]: The instructions and scripts promote the use of npx skills add targeting a remote GitHub repository (https://github.com/akillness/jeo-skills) to install the skill as a plugin. This mechanism involves fetching and potentially executing code from an external source.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines an intake process that gathers user-supplied configuration parameters, which are then passed to execution environments (shell scripts). This creates an attack surface where malicious input could be used to exploit the identified command injection vulnerability.\n
  • Ingestion points: The intake packet described in SKILL.md (Step 1) and environment variables (AGENTS, BUNDLER, PROJECT, PKG_MANAGER) utilized by scripts/install.sh.\n
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat user-supplied data as untrusted or to prevent it from influencing the shell command parameters.\n
  • Capability inventory: The skill utilizes the Bash and Write tools to perform setup and configuration tasks.\n
  • Sanitization: While BUNDLER and PKG_MANAGER are validated using case statements, the AGENTS variable is used unsanitized in a shell context.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 30, 2026, 10:05 AM