runbook-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill manifest defines an attack surface where untrusted data could influence agent behavior through the use of powerful system tools.
  • Ingestion points: Technical documentation requirements and existing file content processed via the Read tool (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within processed data are defined in this manifest.
  • Capability inventory: The skill is granted access to Bash, Write, Edit, Read, and Grep tools, providing significant system interaction and modification capabilities (SKILL.md).
  • Sanitization: The manifest does not specify any sanitization or validation protocols for the content ingested and processed during documentation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:39 PM