claude-devfleet
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's logic is consistent with its stated purpose of agent orchestration and does not exhibit malicious patterns.
- [NO_CODE]: The skill does not include any scripts, binaries, or executable code, consisting only of documentation and tool descriptions.
- [PROMPT_INJECTION]: The skill facilitates the ingestion of user-provided prompts via tools like 'plan_project' and 'create_mission', which are then passed to downstream agents. This represents an indirect prompt injection surface. (1) Ingestion points: prompt arguments in orchestration tools in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: Spawns agents with full tooling in isolated git worktrees. (4) Sanitization: Absent.
Audit Metadata