runbook-authoring
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed exclusively of Markdown documentation, templates, and reference guides. It does not include any scripts (Python, JavaScript, Shell) or compiled binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process to ingest operational data and format it into runbooks, creating a potential attack surface for indirect prompt injection.
- Ingestion points: Operational scenarios, trigger conditions, system dependencies, and tooling constraints defined in SKILL.md.
- Boundary markers: No delimiters or instructions are provided to the agent to distinguish between instructions and ingested data.
- Capability inventory: No tools, subprocesses, network operations, or file system write actions are identified across the skill.
- Sanitization: No data validation or escaping mechanisms are present.
- Risk Assessment: Because the skill lacks any executable capabilities or external interaction tools, the risk of data ingestion being used for an injection attack is negligible and safe within the intended context of documentation drafting.
Audit Metadata