Skills
Navigate
skills/delexw/claude-code-misc/a2a-js-dev/Gen Agent Trust Hub

a2a-js-dev

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists exclusively of instructional documentation and reference guides (Markdown files). It does not contain any executable scripts, binaries, or configuration files that trigger automated code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes an architecture where an agent processes userMessage data from requestContext (untrusted input) and uses an eventBus to publish artifacts and messages (exploitable capabilities).
  • Ingestion points: requestContext.userMessage as defined in SKILL.md and references/sdk-api.md.
  • Boundary markers: None identified in the implementation examples.
  • Capability inventory: The ExecutionEventBus allows publishing Message, Task, and Artifact updates, which can influence downstream agents or be returned to the user.
  • Sanitization: The provided code examples demonstrate direct processing of user text without mentioning sanitization, validation, or escaping of the input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 10:40 AM