Software Development
Builtin Agent Skill
Adding a built-in Agent Skill (an attack technique like ssrf, xxe, rce) that ships hardcoded in RedAmon: classified by the Intent Router, injected into the agent prompt, toggled per project, badged in the chat drawer. Ten layers across agentic and webapp, two of which fail with no error. Trigger: adding or editing a built-in attack skill; a new agentic/prompts/<skill_id>_prompts.py; editing agentic/prompts/classification.py, agentic/prompts/__init__.py build_builtin_skill_workflow, agentic/prompts/skill_parts.py, KNOWN_ATTACK_PATHS in agentic/state.py, or the webapp AttackSkillsSection / AIAssistantDrawer.
- Publisher / source
- samugit83/redamon (found on GitHub top repositories)
- Upstream record
- samugit83/redamon
- Version
- Version 1
- Published
- Publication review
- Approved for publication
- Content fingerprint
9713753b818c7fbf3214ec0e0d3264ef580ec4f7d37cf88b46309adddfff35d5