skills/mikecann/agent-skills/deslop/Gen Agent Trust Hub

deslop

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes and modifies source code files, which can serve as a vector for indirect instructions.
  • Ingestion points: Local repository files identified through git diff or user selection (SKILL.md).
  • Boundary markers: Absent; the instructions do not include safety delimiters or explicit commands to disregard instructions found within the code being cleaned.
  • Capability inventory: File system read/write access and execution of git commands.
  • Sanitization: No validation or sanitization is performed on the content of the files being read.
  • [COMMAND_EXECUTION]: The skill executes git diff to programmatically determine which files have been modified in the current session.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 01:16 PM