distill

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from multiple sources to perform design analysis.
  • Ingestion points: The target argument in the frontmatter and the instructions to gather context from the "current thread or codebase" in the 'Context Gathering' section.
  • Boundary markers: There are no delimiters or specific instructions provided to the agent to treat input data as untrusted or to ignore instructions embedded within the design files or user-provided targets.
  • Capability inventory: The skill instructs the agent to perform design and code modifications, including "Code Simplification" (removing unused code, flattening component trees) and "Information Architecture" changes.
  • Sanitization: There is no evidence of input validation, filtering, or escaping for the data gathered from the codebase or the user argument.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — distill