sdd-init

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core logic of reading and consolidating data from potentially untrusted project files into its configuration and memory backends.\n
  • Ingestion points: The skill reads various technology stack configuration files (e.g., package.json, go.mod, pyproject.toml), user-level agent skill definitions (e.g., ~/.claude/skills/*/SKILL.md), and project-specific instruction files (e.g., CLAUDE.md, .cursorrules, agents.md).\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when the detected content is interpolated into the config.yaml or registry markdown.\n
  • Capability inventory: The skill possesses file system write capabilities (creating openspec/ and .atl/ structures) and utilizes the platform-native mem_save tool for state persistence.\n
  • Sanitization: There is no evidence of sanitization, validation, or escaping of the content ingested from external project files before it is saved to the persistence layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:23 PM