deslop
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze and modify code based on a diff against the main branch, creating a surface for indirect prompt injection if the code changes contain malicious instructions.
- Ingestion points: The agent reads external data in the form of a code diff (
SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the code being analyzed are present.
- Capability inventory: The skill directs the agent to perform code modifications (removing code, comments, and style inconsistencies), which requires file system write capabilities.
- Sanitization: There are no sanitization steps or validation logic to verify the source or content of the diff data.
Audit Metadata