satellite-rig
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is instructional in nature and does not contain executable code, scripts, or automated triggers. It mandates defensive practices such as secret protection and identity verification.- [INDIRECT_PROMPT_INJECTION]: The skill manages external data from manifests and contracts, creating an ingestion surface. 1. Ingestion points: Topology contracts and manifest files (SKILL.md). 2. Boundary markers: None explicitly defined in data format, though instructional boundaries are provided. 3. Capability inventory: Shell CLI execution and file system modification (repair/setup). 4. Sanitization: Relies on manual inspection of installers and planned changes before application.
Audit Metadata