gws-gmail-reply
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the gws command-line interface to perform Gmail operations as described in the metadata and usage examples.
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it processes email content from potentially untrusted sources.
- Ingestion points: The --body flag in SKILL.md receives arbitrary text that may contain malicious instructions.
- Boundary markers: No explicit delimiters or boundary markers are used to isolate the email body from agent instructions.
- Capability inventory: The skill can execute shell commands via the gws binary.
- Sanitization: No input sanitization or validation of the --body content is present in the skill definition.
Audit Metadata