Skills
skills/first-fluke/oh-my-ag/oma-coordination/Gen Agent Trust Hub

oma-coordination

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by propagating user-provided instructions to sub-agents without sanitization or boundary enforcement.\n
  • Ingestion points: Project requirements and task descriptions provided by the user, as referenced in SKILL.md (Step 2) and the examples in resources/examples.md.\n
  • Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore embedded commands within the task strings passed to the oma CLI.\n
  • Capability inventory: The skill uses the oma CLI and the spawn-agent.sh script to execute shell commands and launch new agent sessions with access to the local file system workspaces.\n
  • Sanitization: Absent. There are no instructions to sanitize, escape, or validate user-provided content before it is interpolated into the agent spawning commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 02:58 AM