workflow-refactor
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates an automated research step using
firecrawl:firecrawl_searchandfirecrawl:firecrawl_scrapeto fetch best practices from the web. This creates a surface for indirect prompt injection if the scraped content contains instructions intended to influence the agent's behavior during the refactoring process. - Ingestion points: External web content fetched via
firecrawl:firecrawl_scrapeinSKILL.md(Section: 4. Research Modern Patterns). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the scraped markdown content.
- Capability inventory: The skill employs
ripgrep(rg) for local code analysis and includes instructions for modifying the codebase. - Sanitization: There is no evidence of sanitization, filtering, or validation applied to the external content before it is processed by the agent.
Audit Metadata