Back to skill

Security audit

fulcra-agent-teams

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed team-memory integration with optional automation, and its sensitive behavior is mostly consent-gated and aligned with its purpose.

Install only if you want agents to maintain shared Fulcra team state. Before enabling heartbeat or cron checks, decide the exact team, inbox, allowed data, and duration; avoid sharing raw private files unless explicitly intended, and verify archived inbox messages before deletion.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill explicitly instructs agents to delete inbox messages after archival and only includes a verification step for archive existence, not a user-facing warning about irreversibility or safeguards against accidental deletion of the wrong file. In a shared team-coordination context, mistaken or automated deletion can cause message loss, destroy auditability, and disrupt workflows if archival paths or filenames are wrong.

Cross-Context Output

Medium
Category
Output Handling
Content
- Emphasize that this is definitely optional; alternatively, they can just manually remind you to do team work each time.
- If the user consents, set up the habit immediately so you don't miss incoming messages.

**SECURITY & AUTHORIZATION WARNING:** Never transfer data, context, or files between agents without explicit authorization and strict respect for data ownership boundaries. Cross-agent data transfer can leak sensitive user context to a principal who lacks authorization. Ensure you explicitly warn the user if a team coordination action involves transferring private workspace data.

Within a team's directory, the following OKF structure is used:
- **`team/<team-name>/index.md`**: Directory listing of the team's concepts and members.
Confidence
90% confidence
Finding
Cross-agent data transfer

Session Persistence

Medium
Category
Rogue Agent
Content
**Background Heartbeats:**
- **Require Consent:** You must explicitly ask the user for permission before enabling automated background inbox checks.
- If the user approves, add a task to your local workspace's `HEARTBEAT.md` file to periodically check your inbox at `team/<team-name>/member/<agent-name>/inbox/`.
- Ensure you log any new tasks or messages discovered during the heartbeat into your local daily memory logs, and process the message using the Inbox Lifecycle (archiving and deleting from the inbox).

**Isolated Cron Jobs:**
Confidence
87% confidence
Finding
add a task to

Session Persistence

Medium
Category
Rogue Agent
Content
Agents can collaborate and share memory using a shared `team/<team-name>/` prefix in the Fulcra datastore. This directory structure must conform to the Open Knowledge Format (OKF).

### Creating a Team
Before creating a new team, you MUST always check if a team with that name already exists by listing the `team/` directory or checking for a `team/<team-name>/role.md` file. Do not accidentally overwrite or recreate an existing team structure. If the team already exists, simply join it.

### Joining a Team
When joining a team, do not assume your role. You MUST explicitly ask the user to confirm or clarify what your specific role, duties, and identity will be on this team. Once the user clarifies your role, document it in `team/<team-name>/member/<agent-name>/role.md`.
Confidence
83% confidence
Finding
write or recreate an existing team structure. If the team already exists, simply join it. ### Joining a Team When joining a team, do not assume your role. You MUST explicitly ask the user to confirm

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.