effect-service-design

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project data such as source code, architecture documents, and local configuration files. This represents a surface for indirect prompt injection, which is typical for codebase auditing tools.
  • Ingestion points: Reads AGENTS.md, architecture documentation, and the target project source code as specified in SKILL.md (Step 1) and references/AUDIT.md (Step 1).
  • Boundary markers: The instructions do not specify explicit delimiters or 'ignore embedded instructions' warnings when the agent processes these external files.
  • Capability inventory: The skill focus is limited to code analysis and generation within the chat context. It does not invoke shell commands, file-write operations, or network requests based on the analyzed data.
  • Sanitization: There are no explicit instructions to sanitize or filter the ingested content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 02:12 PM
Security Audit — agent-trust-hub — effect-service-design