deslop
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes
git diff mainto identify changes. While this is a standard operation for a code-cleaning tool, it involves subprocess execution. - [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted data. * Ingestion points:
SKILL.mddescribes readinggit diffoutput and full file contents from the current branch. * Boundary markers: Absent; there are no specific instructions or delimiters used to prevent the agent from following commands embedded in the code it is cleaning. * Capability inventory: Subprocess execution (git) and source code modification. * Sanitization: Absent; the skill does not specify any sanitization or validation of the ingested code content.
Audit Metadata