onenote-security-basics
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a procedural workflow for auditing security configurations and third-party documentation, which introduces a surface where malicious instructions embedded in those documents could influence the agent's behavior.
- Ingestion points: Files and documentation accessed using the
Read,Glob, andGreptools as specified in the 'Instructions' and 'Tool Discipline' sections ofSKILL.md. - Boundary markers: The instructions lack specific boundary markers or 'ignore' directives to help the agent distinguish between data to be audited and instructions to be followed within external files.
- Capability inventory: The skill allows for the modification of files via the
WriteandEdittools based on the results of the audit. - Sanitization: There are no explicit validation or sanitization steps defined for processing the content of ingested external files before they impact agent output or repository modifications.
Audit Metadata