ss-troubleshooting-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (issue links, alert IDs, and problem descriptions) as its primary input, creating a potential surface for indirect prompt injection.
- Ingestion points: The
Problem sourceinput described inSKILL.mdcaptures external text or content from URLs. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for the input data.
- Capability inventory: The workflow has the ability to trigger code generation (
ss-coding), branch creation (ss-create-branch), and pull request submission (ss-create-pr). - Sanitization: The instructions do not define specific sanitization or filtering logic for the input source.
- Context: This risk is effectively mitigated by the skill's design, specifically 'Iron Rule 2,' which requires human confirmation of the root cause before any code changes or branches are created. This ensures the agent does not act autonomously on potentially malicious instructions embedded in the problem description.
Audit Metadata