payabli-getting-started

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides numerous links to official documentation on the docs.payabli.com domain. These are identified as trusted vendor resources directly related to the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read project manifest files and user-provided goals to generate an integration plan. This represents an attack surface where untrusted content from the project could influence the agent's output, though the resulting capability is limited to writing a markdown file.
  • Ingestion points: User-stated goals in conversation and local project manifest files (Step 1 and Step 6).
  • Boundary markers: None explicitly defined to separate untrusted data from instructions.
  • Capability inventory: The skill is capable of writing the payabli-integration.md file to the repository root (Step 7).
  • Sanitization: No explicit sanitization or validation of the ingested manifest data or user input is described before it is written to the integration plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 05:07 PM