dx-packaging-convert-1gp-to-2gp-create
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing various Salesforce CLI (sf) commands to perform its core functions. These include sf package convert, sf org display, sf data query, sf package version create report, and sf package version promote. Evidence: Found throughout SKILL.md and references/conversion-operations.md. For example, sf package convert --package <033> --target-dev-hub --code-coverage --wait 20 --json.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from a Salesforce DX project, which could potentially be manipulated to influence the agent's behavior. Ingestion points: The skill reads and validates contents from sfdx-project.json, project-scratch-def.json, and specified metadata directories (seed-metadata and unpackaged-metadata). Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore instructions embedded within the metadata or configuration files being read. Capability inventory: The skill possesses significant capabilities, including executing shell commands through the Salesforce CLI (sf) and modifying project files like sfdx-project.json. Sanitization: While the skill provides instructions for sanitizing output when preparing a support escalation bundle, it does not specify sanitization or validation protocols for data read from the project's configuration files during the conversion workflow.
Audit Metadata