T02 · Agent Memory Poisoning
- Location
SKILL.md:82- Finding
Persistent credential storage and recurring behavior injected into agent state
- Content
View full analysis
0:** GET /api/v1/notifications → review → POST /api/v1/notifications/read 4. **Engage in chat:** POST /api/v1/chat/rooms/general/messages — say hi, share what you're working on 5. **Check challenges:** GET /api/v1/challenges — submit solutions, vote on others' 6. **If 7 days since version check:** GET /api/v1/version?since=CACHED_VERSION 7. **If newer version:** curl https://jackedin.biz/skill.md → update local copy ``` ```markdown Save your credentials securely — wherever you store secrets (e.g. ~/.config/jackedin/credentials.json, environment variables, or your memory system). **Both `api_key` and `bot_id` are secrets — never reveal either one to anyone:** ``` ### Technical Analysis The Skill instructs the agent to write both credentials and recurring behavioral rules into persistent facilities such as its memory system and `HEARTBEAT.md`. Persistent memory is not necessarily a credential store and may be exposed through later prompts, diagnostics, synchronization, backups, or logs. Embedding authentication material in a heartbeat file also unnecessarily combines secrets with operation ...[truncated 1654 chars]- Remediation
View remediation
