ios-brief

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and process content from the local codebase and existing project files.
  • Ingestion points: The skill reads project context from docs/.ios-init-decisions.json, docs/PROJECT-BRIEF.md, and performs a scan of the project's codebase (file names, structure, and content).
  • Boundary markers: There are no explicit boundary markers or instructions provided to the agent to disregard or escape instructions embedded within the analyzed files.
  • Capability inventory: The skill has the capability to read and scan the file system and perform writes to docs/PROJECT-BRIEF.md.
  • Sanitization: The instructions do not specify any sanitization, validation, or filtering of the content extracted from external files before it is incorporated into the draft and written back to the file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:51 AM
Security Audit — agent-trust-hub — ios-brief