The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/call-txn-management-apis.sh executes local system commands including curl, jq, awk, and the Salesforce CLI (sf). These are used to dynamically discover the org's API version, retrieve OAuth bearer tokens via authorized CLI sessions, and perform REST API calls to the Salesforce instance. This is the primary intended function of the skill and follows secure authentication practices by avoiding hardcoded credentials.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and display responses from Salesforce REST API endpoints, which constitutes a potential attack surface for indirect prompt injection if the remote data were compromised.
Ingestion points: API response bodies are fetched from Salesforce Connect REST resources in scripts/call-txn-management-apis.sh.
Boundary markers: The script outputs the response within a structured JSON object to provide context to the agent.
Capability inventory: The skill can perform network requests (curl) and read local files for payloads.
Sanitization: The script uses jq to parse and validate the JSON structure of responses before they are displayed. Given that the API calls target the user's own authorized Salesforce instance, the source is considered high-trust.

revenue-cloud-txn-management-apis