bot-process-control

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses bash to execute diagnostic commands such as launchctl list, ls ~/Library/LaunchAgents, and pgrep. These are used to verify that no conflicting instances of the bot are running on the local workstation.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains 'Self-Evolving Skill' and 'Post-Execution Reflection' instructions that direct the agent to modify its own SKILL.md file based on runtime experiences. This self-modification loop creates an attack surface for logic drift or instruction poisoning if the agent interprets external feedback incorrectly. Ingestion points: Agent internal reflection process. Boundary markers: Absent. Capability inventory: Read and Bash tools for modifying local files. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 02:12 AM