recommending-devops-tests
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the
sf(Salesforce CLI)data querycommand to fetch DevOps Center metadata. This utilizes legitimate, vendor-provided tooling for its intended purpose. - [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection as it processes untrusted data in the form of commit diffs.
- Ingestion points: Commit diffs are ingested and analyzed during the 'Reasoning steps' phase (SKILL.md).
- Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions to encapsulate the untrusted diff content.
- Capability inventory: The skill can execute SOQL queries via the
sfcommand and display results to the user. - Sanitization: No explicit sanitization, validation, or escaping of the diff content is performed before the agent reasons over it.
Audit Metadata