deslop
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (
git diff) to identify the set of files to be processed. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it reads and presents content from the local repository.
- Ingestion points: Files read during the 'Scan for Slop Patterns' phase in
SKILL.md. - Boundary markers: Lacks explicit delimiters or 'ignore' instructions for the content being processed from files.
- Capability inventory: Shell command execution (
git) and file modification capabilities via the 'Apply Approved Removals' process. - Sanitization: The risk is mitigated by the requirement for explicit user approval for every suggested change, preventing automated malicious modifications.
Audit Metadata