platform-metadata-api-context-get

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is a technical reference library containing markdown instructions and JSON metadata descriptions for over 600 Salesforce API types. It does not include any executable code or binary components.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from technical JSON documentation files.
  • Ingestion points: The agent is instructed to read from files in the assets/metadata_api/ directory using the Read tool or programmatic scripts as described in SKILL.md and examples/README.md.
  • Boundary markers: The instructions emphasize section-specific consumption for token optimization but do not explicitly provide delimiters or 'ignore instructions' warnings for the content of the metadata descriptions.
  • Capability inventory: The skill configuration in SKILL.md and code examples identify requirements for jq, node, python3, and sf CLI tools to parse local files.
  • Sanitization: No manual sanitization is described, as the content consists of static, internal documentation files generated from technical schema files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 09:36 PM