Skills
Navigate
skills/orcaqubits/agentic-commerce-skills-plugins/ap2-human-present-flow/Gen Agent Trust Hub

ap2-human-present-flow

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch protocol specifications and reference implementations from ap2-protocol.org and a GitHub repository (google-agentic-commerce/AP2) to guide the code generation process.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation and code samples from external websites, which creates a vulnerability surface where instructions hidden in those external sources could potentially influence the agent's actions.
  • Ingestion points: WebFetch and WebSearch tools are used to retrieve documentation and code from ap2-protocol.org and GitHub as specified in SKILL.md.
  • Boundary markers: No explicit delimiters or boundary instructions are present to differentiate external data from skill instructions.
  • Capability inventory: The skill allows the use of Bash, Write, and Edit tools which can modify the environment or local files.
  • Sanitization: The skill does not define specific validation or sanitization routines for the data fetched from remote sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:33 PM