ai-slop-cleaner
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process code from external sources such as branch diffs and file lists, which creates a surface for potential indirect prompt injection.
- Ingestion points: The workflow involves reading local code files and analyzing differences between git branches.
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions that might be embedded within the source code being analyzed.
- Capability inventory: The skill directs the agent to execute local tools, including linting, type-checking, and running unit or integration tests, which involves executing code within the local environment.
- Sanitization: The instructions do not specify any sanitization or validation of the ingested code content before it is processed or used to trigger local command execution.
Audit Metadata