finops
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, presenting a potential surface for indirect prompt injection.
- Ingestion points: External data and web content accessed via BrowserOS as noted in SKILL.md.
- Boundary markers: No specific boundary markers or delimiters for untrusted input are defined in the instructions.
- Capability inventory: The skill utilizes terminal execution via ExecutionProxy and file writing through the MemoryStore interface (Obsidian docs/departments/).
- Sanitization: The instructions mandate redacting secrets and PII from external content before further processing.
- [SAFE]: The skill follows established company framework protocols for deterministic execution and least privilege access. No malicious code, credential theft, or unauthorized network operations were detected.
Audit Metadata