skills/dropseed/plain/plain-upgrade/Gen Agent Trust Hub

plain-upgrade

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the uv run plain command to perform package upgrades, fetch changelogs, sync agent rules, and run project health checks. These operations are local to the project environment and consistent with the skill's purpose.
  • [EXTERNAL_DOWNLOADS]: The skill uses the uv package manager to download and install package updates from remote registries. This is a standard dependency management task.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it instructs the agent to read and follow 'Upgrade instructions' derived from external package changelogs. 1. Ingestion points: Data enters the context via the output of the uv run plain changelog command (SKILL.md). 2. Boundary markers: There are no markers or warnings instructing the agent to ignore potentially malicious instructions within the changelog text. 3. Capability inventory: The skill has access to subprocess execution via uv run plain and the ability to modify project files. 4. Sanitization: No validation or sanitization of the changelog content is performed before the agent processes the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 06:41 AM
Security Audit — agent-trust-hub — plain-upgrade