quantum-safe-file-attestation
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it accepts user-provided freeform data that is incorporated into the agent's operational context.
- Ingestion points: The
metadata(object) andartifact_name(string) parameters in theattest_artifactaction. - Boundary markers: The instructions lack explicit delimiters or guidance to ignore embedded instructions within the metadata fields.
- Capability inventory: The skill's functionality is limited to remote API calls to the vendor's infrastructure and does not involve local command execution or file system write access.
- Sanitization: No input validation or content filtering mechanisms are defined for the ingested data.
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to install related components from the vendor's official GitHub repository (
AgentPMT/agent-skills) using platform-standard tools such asnpxandopenclaw.
Audit Metadata