deepinit

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read and follow instructions from the local file .agents/workflows/deepinit.md.\n
  • Ingestion points: The file .agents/workflows/deepinit.md is loaded into the agent's context as the primary source of operational instructions.\n
  • Boundary markers: The instructions do not include delimiters or specific guidance to the agent to treat the workflow file as untrusted data or to ignore potentially malicious embedded instructions.\n
  • Capability inventory: The skill description indicates the capability to generate files (AGENTS.md, ARCHITECTURE.md) and create directory structures (docs/), implying write permissions to the file system.\n
  • Sanitization: There is no evidence of content validation or sanitization before the agent executes the steps defined in the workflow file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 09:30 PM
Security Audit — agent-trust-hub — deepinit