deslop
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code content from git diffs, which could potentially contain embedded instructions designed to influence the AI's behavior during the 'deslop' process.
- Ingestion points: The skill ingests data through the command
git diff main...HEAD(SKILL.md). - Boundary markers: No explicit delimiters or warnings are provided to the agent to disregard instructions found within the code diff.
- Capability inventory: The skill has the capability to review and modify files in the local repository based on the ingested data.
- Sanitization: The skill does not perform any sanitization or validation of the code content before analysis and modification.
- [COMMAND_EXECUTION]: The skill utilizes the local shell to execute
git diff main...HEAD. While this is an expected operation for the skill's functionality, it involves the execution of commands that interact with the local filesystem and repository state.
Audit Metadata