ai-design-slop-remover
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans user-provided UI source files, which serves as an ingestion point for untrusted data.
- Ingestion points: The scripts detect-slop.cjs and analyze-structure.cjs read files from user-defined paths.
- Boundary markers: The instructions in SKILL.md and rules/safe-editing.md mandate treating scanned content as data only and ignoring embedded instructions.
- Capability inventory: The agent can execute local Node.js scripts and write reports, but is restricted from network or production access.
- Sanitization: The instructions provide a strict safety boundary to prevent the execution of content found within the files.
- [COMMAND_EXECUTION]: The skill executes internal Node.js helper scripts to perform analysis.
- Evidence: SKILL.md workflow calls detect-slop.cjs and analyze-structure.cjs.
- Context: These scripts are part of the skill's package and perform static regex-based scanning and structure counting without involving remote resources or unauthorized command interpolation.
Audit Metadata