deslop
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to manage the scope of its operations and verify code integrity. It uses
git diffandgit merge-baseto identify modified files and executes project-specific scripts likebun run type-checkandbun run testto ensure changes do not break the build. - [INDIRECT_PROMPT_INJECTION]: The skill processes and rewrites content from external sources such as source code files and prose documents, which creates a surface for indirect prompt injection.
- Ingestion points: Reads project source files, READMEs, PR descriptions, and other prose surfaces in
SKILL.md. - Boundary markers: The skill lacks explicit instructions or delimiters to prevent the agent from following malicious instructions that might be embedded in the data being processed.
- Capability inventory: The agent can modify local files and execute shell commands (
git,bun,tsc) as detailed in the Workflow section ofSKILL.md. - Sanitization: There are no documented mechanisms for sanitizing or validating the input data before it is processed by the agent.
Audit Metadata