skills/rpamis/comet/comet-native/Gen Agent Trust Hub

comet-native

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external source materials such as files, attachments, or links provided by the user. This creates a surface for indirect prompt injection where instructions embedded in these materials could attempt to subvert the agent's behavior.\n
  • Ingestion points: User-provided files, attachments, and links used as requirements sources (identified in SKILL.md under the 'Shape' section).\n
  • Boundary markers: The skill explicitly instructs the agent that instructions found within source materials must be treated as content only and cannot override the user's request or project rules.\n
  • Capability inventory: The skill executes shell commands via the comet CLI and writes to project files like brief.md and specs/.\n
  • Sanitization: Relies on the agent's ability to distinguish between data content and instructions as directed by the skill.\n- [COMMAND_EXECUTION]: The skill performs shell command execution using the comet CLI (e.g., comet native, comet task) to manage the workflow. It passes user-provided input, such as the original request, directly into command arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 01:53 PM
Security Audit — agent-trust-hub — comet-native