Skills
Navigate
skills/specterops/skills/oc2-bot-development/Gen Agent Trust Hub

oc2-bot-development

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The bot runtime API processes data from remote implants which are untrusted sources.
  • Ingestion points: on_new_implant and on_task_response handlers in references/bot-runtime-api.md receive objects containing data like hostnames, usernames, and command responses.
  • Boundary markers: None are mentioned or used in the documentation.
  • Capability inventory: The API allows scheduling high-impact tasks such as ExecCommandTask, ExecShellcodeTask, UploadTask, and GetSystemTask as documented in references/bot-runtime-api.md.
  • Sanitization: No sanitization or validation logic is present in the examples within references/bot-examples.md.
  • [DYNAMIC_EXECUTION]: The system uses dynamic loading to execute bot logic at runtime.
  • Evidence: references/bot-development.md specifies that the bot engine loads and executes BaseBot subclasses from Python files located in the shared/bots/on directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:15 PM