suanli-job
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local script,
scripts/call.sh, to communicate with the service API. This script executescurlto send data andpython3to generate timestamps for request headers.- [EXTERNAL_DOWNLOADS]: The skill interacts with official endpoints includingopenapi.suanli.cnfor orchestration andharbor.suanleme.cnfor container images. These are legitimate service domains belonging to the vendor for managing and deploying compute workloads.- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the platform, such as execution logs and task status reports, which could potentially contain untrusted content from the task environment. - Ingestion points: API responses from
/api/deployment/task/point_logand/api/task/job/detailprocessed via the command-line caller. - Boundary markers: The skill does not explicitly define delimiters to isolate external log data from the agent's core instructions.
- Capability inventory: The agent can trigger job creation, updates, and termination via the provided API wrapper scripts based on its findings.
- Sanitization: No explicit sanitization or filtering of external API data is performed prior to ingestion.
Audit Metadata