deploy-status-report
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external deployment logs and failure analysis reports, which could potentially contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: External data is ingested via MCP tools such as
delivery:delivery-spinnakeranddelivery:delivery-execution-failure-analysis(SKILL.md). - Boundary markers: The skill does not explicitly define delimiters or specific 'ignore' instructions for the content retrieved from these external tools.
- Capability inventory: The agent has the capability to generate reports and upload them to cloud storage (S3) or deliver them via chat platforms.
- Sanitization: While no specific text sanitization is mentioned, the skill mandates 'Deterministic math first' for classifications (SKILL.md, Design Principles), which reduces the model's reliance on potentially poisoned prose for its primary reporting logic.
Audit Metadata