label-scheme-management
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external repositories which could potentially contain malicious instructions.
- Ingestion points: Untrusted data enters the agent context via
list_label,list_issues, andget_labeltools, which retrieve label names, colors, and descriptions from a repository. - Boundary markers: The skill contains explicit instructions to 'Present the full intended set of changes before the first call' and to 'get explicit agreement naming that label' before removal, which serves as a human-in-the-loop boundary.
- Capability inventory: The skill possesses the capability to modify the repository environment using the
label_writetool (create, update, delete methods). - Sanitization: There is no explicit mention of data sanitization or escaping for the retrieved label content before it is interpolated into the agent's decision-making process.
Audit Metadata