recall

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to manage project state by reading internal tool files such as .omc/notepad.md and .omc/project-memory.json. These are session-specific artifacts used for context recovery and do not expose sensitive user credentials or system configurations.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files that could potentially be modified by external actors. However, it uses this data solely for status reporting and task planning rather than direct execution or command construction.
  • Ingestion points: Reads from .omc/ state files and repository rules (AGENTS.md, CLAUDE.md) as specified in SKILL.md.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: No file-writing, network operations, or subprocess executions are defined within the skill.
  • Sanitization: None specified; the skill relies on reporting the content of artifacts to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 07:21 PM