deepinit

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill directs the agent to read and follow instructions from a file located at .agents/workflows/deepinit.md. This pattern represents an indirect prompt injection surface, as the agent is instructed to follow the content of this file "step by step."
  • Ingestion points: .agents/workflows/deepinit.md (referenced in SKILL.md)
  • Boundary markers: Absent; the agent is not provided with delimiters or instructions to ignore embedded commands within the workflow file.
  • Capability inventory: File system write operations for creating project structures like AGENTS.md and ARCHITECTURE.md (as described in the skill metadata).
  • Sanitization: No sanitization or validation of the workflow file's content is specified.
  • [NO_CODE]: The skill consists only of markdown instructions and does not contain any executable scripts, binaries, or code files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 09:35 PM