oma-pm
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user requests and project requirements to generate task plans that contain executable command strings for downstream agents.
- Ingestion points: User requests, product goals, and project context are read from memory in
SKILL.mdandresources/execution-protocol.md. - Boundary markers: The skill uses structured JSON templates (
resources/task-template.json) and specific markdown sections to delimit data, which helps mitigate accidental instruction following. - Capability inventory: The skill is limited to reading requirements and writing plan artifacts to the
.agents/results/directory; it does not execute the generated commands itself. - Sanitization: There is no explicit sanitization of user-provided requirements before they are interpolated into the task descriptions or acceptance criteria in the generated JSON plan.
Audit Metadata