The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the sf CLI v2 to perform Salesforce operations, including sf project deploy start, sf org display, sf apex run test, and sf agent publish. These are standard tools for the skill's stated purpose of Salesforce DevOps automation.
Evidence: SKILL.md and references/deploy.sh list numerous CLI commands for deployment, authentication, and testing.
[EXTERNAL_DOWNLOADS]: The README.md provides installation instructions via npx skills add Jaganpro/sf-skills, which targets the author's own repository. This is the intended distribution method for these agent skills.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze output from the sf CLI, such as deployment reports and error messages, which could theoretically contain malicious instructions if the target Salesforce org or metadata is compromised.
Ingestion points: Deployment success/failure reports and CLI JSON outputs are processed to generate summaries (referenced in SKILL.md and references/deployment-report-template.md).
Boundary markers: None identified; the instructions do not specify delimiters or warnings to ignore embedded instructions in the CLI output.
Capability inventory: The skill has the capability to execute shell commands via the sf CLI, modify local metadata files, and potentially write data back to the Salesforce org (found in SKILL.md and references/deploy.sh).
Sanitization: There is no evidence of specific sanitization or filtering of the CLI output before it is processed by the agent to provide the next steps or reports.

sf-deploy