skills/shipshitdev/skills/scaffold/Gen Agent Trust Hub

scaffold

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documentation suggests delegating project initialization to a vendor-provided package (@shipshitdev/v0) using the npx command. This operation fetches and executes code from the official NPM registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and replicate patterns from existing files in the repository, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: Local codebase files and implementation examples identified during the search step (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore malicious or non-standard instructions that might be embedded in the examples.
  • Capability inventory: Modification and creation of local source files, test files, and package configurations (SKILL.md).
  • Sanitization: Absent; the skill does not include steps to sanitize or validate the content of the patterns being followed before they are used to generate new code.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 04:47 PM