maestro-odyssey
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user-provided intent strings and has access to powerful tools like Bash, Edit, and Write.
- Ingestion Point: The 'intent' argument passed to the skill in SKILL.md.
- Boundary Markers: Absent; no explicit delimiters or instructions to ignore embedded commands are used for the input string in the instructions.
- Capabilities: Access to Bash (command execution), Edit and Write (file system modification), and spawn_agent (autonomy) as listed in the allowed-tools section of SKILL.md.
- Sanitization: Absent; no explicit sanitization or validation of the input string is mentioned before processing.
Audit Metadata