skills/capire/skills/cap-developer/Gen Agent Trust Hub

cap-developer

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @sap/cds-dk package from the official NPM registry. SAP is a well-known technology vendor, and this package is a standard development tool for the CAP ecosystem.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard development CLI tools including the SAP CDS CLI (cds), Maven (mvn), and NPM (npm). These tools are used for project initialization, building, and running development servers, which are expected activities for this type of skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to analyze potentially untrusted project data.
  • Ingestion points: The agent is instructed to read source code (JavaScript, Java), model definitions (CDS), and configuration files (package.json, pom.xml) from the local project directory.
  • Boundary markers: There are no explicit instructions for the agent to use delimiters or specific safety markers to differentiate between its core instructions and the code being analyzed.
  • Capability inventory: The agent has the capability to execute shell commands and modify local files, creating a potential path for exploitation if malicious instructions are embedded in the project files.
  • Sanitization: The skill does not define any specific sanitization or validation protocols for handling content retrieved from the file system or external documentation sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 07:07 PM