write-runbook
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external service code, configuration, and dependencies to generate a runbook. This ingestion process is vulnerable to indirect prompt injection if the source data contains malicious instructions meant to override the agent's behavior.
- Ingestion points: Service code, config, and dependency definitions (referenced in SKILL.md description).
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore instructions embedded within the processed data.
- Capability inventory: The skill does not include any scripts, network operations, or privileged commands of its own; it is limited to text generation.
- Sanitization: The skill lacks validation or sanitization mechanisms for the external data it processes.
Audit Metadata