deslop
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard git commands (
git diff,git add,git status) to identify and manage code changes. These commands are necessary for the skill's primary function of code simplification. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes untrusted data from the local repository.
- Ingestion points: The agent reads the output of
git diff(Step 1) and the full content of source files (Step 2). - Boundary markers: There are no defined delimiters or instructions to distinguish the code being analyzed from the agent's core instructions.
- Capability inventory: The skill has the capability to read any file in the diff and write modifications to those files.
- Sanitization: There is no logic provided to sanitize file content or filter out instructions that may be embedded in comments or strings within the processed files.
Audit Metadata