api-status-communication
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to request and process external content provided by the user, creating an entry point for indirect prompt injection attacks.
- Ingestion points: In
SKILL.md, under 'Clarifying questions', the agent is instructed to "request its URL and the full update history of the last 2-3 incidents." - Boundary markers: The instructions do not define specific boundary markers or 'ignore' commands to help the agent distinguish between its own system instructions and potentially malicious instructions embedded within the retrieved incident history or external URL content.
- Capability inventory: The skill is primarily focused on generating design documentation and communication strategies. While it involves processing text, it does not invoke high-risk system commands, network exfiltration tools, or file system modifications.
- Sanitization: The workflow lacks defined sanitization or validation steps for the content retrieved from external status pages or incident histories.
Audit Metadata