gccli
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installing the
@mariozechner/gcclipackage from the public NPM registry. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The agent reads external data from Google Calendar, such as event summaries and descriptions, which could contain untrusted content.
- Boundary markers: None are defined in the skill instructions to distinguish between instructions and data.
- Capability inventory: The skill facilitates file system interaction for credential management and network access to Google APIs.
- Sanitization: No specific sanitization or filtering of calendar content is mentioned.
- [DATA_EXPOSURE]: The skill documentation identifies specific local paths where sensitive OAuth credentials and account tokens are stored:
~/.gccli/credentials.jsonand~/.gccli/accounts.json.
Audit Metadata