dependency-updater

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill encourages the installation and use of tools like 'taze', 'pip-review', and 'cargo-audit' from GitHub repositories and package registries that are not included in the 'Trusted External Sources' list provided in the security skill instructions.
  • COMMAND_EXECUTION (MEDIUM): The script 'scripts/run-taze.sh' executes external tools with arbitrary arguments provided by the agent or user. Furthermore, the 'Nuclear Reset' instructions in the README involve potentially destructive commands like 'rm -rf' on directories, which could lead to significant data loss if executed without proper validation or human oversight.
  • PROMPT_INJECTION (LOW): The skill possesses a surface for indirect prompt injection (Category 8). 1. Ingestion points: Project manifests such as package.json and requirements.txt are read from the workspace. 2. Boundary markers: None are implemented to distinguish between package data and instructions. 3. Capability inventory: The skill can execute various package manager commands and shell scripts. 4. Sanitization: There is no evidence of sanitization for strings extracted from package files before they are presented to the agent or passed to execution tools.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 04:58 PM