The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from external SAP Analytics Cloud models and dimension members, which constitutes a surface for indirect prompt injection.
Ingestion points: Data enters the agent's context through Table.getDataSource().getData(), PlanningModel.getMembers(), and result sets from data actions as documented in references/api-reference.md and references/analytics-designer-planning.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested data were found in the skill instructions.
Capability inventory: The skill utilizes capabilities such as NavigationUtils.openUrl(), Table.getPlanning().submitData(), and DataAction.execute() to interact with the SAC environment.
Sanitization: The provided documentation and scripts do not explicitly describe sanitization or validation routines for data values or dimension properties retrieved from the model.
[DYNAMIC_EXECUTION]: The skill provides detailed instructions and API references for writing and executing platform-specific scripts (Advanced Formulas and Analytics Designer JavaScript).
Evidence: The skill includes comprehensive guides for Advanced Formula scripts (references/advanced-formulas.md) and Analytics Designer JavaScript patterns (references/javascript-patterns.md). These are documented as standard platform features for SAP Analytics Cloud developers and consultants to automate planning workflows.
[SAFE]: All external references point to trusted domains, including official SAP documentation (help.sap.com, learning.sap.com), SAP community resources, and the maintainer's repository on GitHub. No evidence of malicious obfuscation, persistence, or privilege escalation was detected. The browser automation via CDP (Chrome DevTools Protocol) for triage is documented with explicit safeguards, requiring user consent and approval for writeback operations.

sap-sac-planning