create-github-issue-feature-from-specification
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from specification files to drive tool actions.
- Ingestion points: The
${file}variable inSKILL.mdindicates untrusted file content is loaded. - Boundary markers: There are no boundary markers or instructions to ignore embedded commands defined to prevent the agent from following commands hidden in the specification.
- Capability inventory: The skill has write access to GitHub via the
create_issueandupdate_issuetools. - Sanitization: The instructions do not define any filtering or validation for the content extracted from the specification.
Audit Metadata