gws-people

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gws binary to execute operations against the Google People API. This usage is explicitly declared in the metadata and is appropriate for the skill's stated purpose of managing contacts and profiles.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads potentially untrusted data from contact records (e.g., names, biographies, and organizations via methods like people.get or people.searchContacts in SKILL.md). There are no explicit boundary markers or sanitization procedures defined within this file. However, the risk is negligible as the skill's inventory of capabilities is limited to authenticated Google People API calls and does not include dangerous primitives such as arbitrary code execution or direct file system manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — gws-people