oc-verify
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of various development and testing commands on the local system.
- Evidence: The skill instructions and verification matrix involve running
git,pnpm,go,vitest, andplaywright. - Context: These operations are intended for local branch validation and integration testing within the krillinai development environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external repository data which could contain malicious instructions.
- Ingestion points: The skill reads
git diffoutput,.github/workflows/ci.yml, andreferences/verification-matrix.mdinSKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within the analyzed files or diffs.
- Capability inventory: The skill utilizes
pnpm,go,vitest,playwright, andgitto perform validation tasks as detailed inreferences/verification-matrix.md. - Sanitization: The instructions do not specify any sanitization or validation logic for the ingested file content before it is used to influence the agent's actions.
Audit Metadata