openteam-control
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the '@afumu/openteamcli' package from the NPM registry. This is a vendor-supplied tool required for the skill's primary functionality.
- [COMMAND_EXECUTION]: The skill makes extensive use of the 'openteamcli' command-line tool to manage local processes and interact with the OpenTeam platform, including starting a local daemon and posting tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process responses from external AI agents, creating a potential surface for indirect prompt injection where instructions embedded in chat replies could influence the agent's behavior.
- Ingestion points: Output from 'openteamcli task read' (SKILL.md).
- Boundary markers: None explicitly mentioned for processing the chat results.
- Capability inventory: Shell command execution via 'openteamcli' (SKILL.md).
- Sanitization: Instructions for users to avoid including private information in task content (SKILL.md).
Audit Metadata