skills/bigdra50/dotfiles/disk-usage/Gen Agent Trust Hub

disk-usage

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute various mise run disk-usage subcommands. These commands are intended to retrieve disk usage statistics and identify potential files for deletion. It also explicitly calls /usr/bin/du and /bin/df to avoid path-based alias hijacking.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and processing the output of shell commands. Maliciously crafted file names or tool outputs could theoretically be used to influence the agent's interpretation of the data.
  • Ingestion points: Command output from mise run disk-usage (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify delimiters or markers to wrap the tool output.
  • Capability inventory: The skill is granted access to the Bash, Read, and Glob tools.
  • Sanitization: No explicit sanitization, validation, or escaping of the command output is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 05:40 PM