loop-deliver
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by ingesting workspace context and current host information to generate implementation artifacts.
- Ingestion points: The skill inspects the workspace and host environment as part of its 'On invoke' logic in SKILL.md.
- Boundary markers: No explicit delimiters are defined to isolate potentially untrusted workspace content from the agent's instructions.
- Capability inventory: The skill is capable of compiling and writing multiple project artifacts, including executors, supervisors, ledgers, directives, and operations files.
- Sanitization: The skill does not specify explicit sanitization or filtering of external workspace data before processing.
- [SAFE]: The skill provides explicit safety instructions to the agent to avoid executing generated runtime nodes and establishes 'Authority' presets that restrict high-risk operations like pushing to remote repositories or exposing secrets.
Audit Metadata