orca-cve-blast-radius
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate security analysis by querying for assets affected by specific CVEs using provided tools like
discovery_searchandget_asset_by_id. All resource patterns and tools are consistent with the vendor's ('orcasecurity') stated purpose. - [DATA_EXPOSURE_&_EXFILTRATION]: The skill accesses asset metadata, attack path information, and alert summaries. This is performed using authorized tools and results are presented to the user within the agent's environment. No sensitive file paths (like ~/.ssh or ~/.aws) or unauthorized network exfiltration attempts were detected.
- [COMMAND_EXECUTION]: While the skill mentions generating remediation scripts (Terraform, Ansible, etc.), these are written to local files for the user to review and execute manually. There is no evidence of automatic or hidden shell command execution.
- [PROMPT_INJECTION]: The instructions do not contain attempts to override safety guidelines or bypass agent constraints. The 'CRITICAL' instruction in the Proactive Remediation section is a formatting instruction for the agent's behavior, not a security bypass.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or remote script execution. All data is retrieved via the provided MCP tools.
Audit Metadata