odyssey4me/google-sheets
Read, write, and format Google Sheets spreadsheets. Manage cell values, ranges, formulas, pivot tables, and charts. Use when asked to update a gsheet, edit a Google spreadsheet, add formulas, or work with spreadsheet data.
71
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill instructs storing and passing OAuth client_id/client_secret (including examples showing --client-secret and config file fields), which encourages embedding secrets verbatim in commands/files and thus exposes them.
Where we found it
--client-secret
command · 6 sites
The skill documents and implements a command-line argument --client-secret that accepts OAuth client secrets directly on the command line, which exposes secrets in shell history and process listings.
[REDACTED]
secret · 1 site
The SKILL.md shows a config file example with client_secret field containing a placeholder value, encouraging users to embed secrets in config files.
SKILL.md
50
[REDACTED]
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill's values read command (SKILL.md examples and scripts/google-sheets.py cmd_values_read which calls service.spreadsheets().values().get(...)) fetches arbitrary Google Sheets content (user-generated/untrusted data from third-party Google-hosted documents) that the agent is expected to read and could materially influence subsequent actions, so it exposes the agent to indirect prompt-injection risk.
Where we found it
www.googleapis.com
domain · 12 sites
The plugin calls the Google Sheets API at www.googleapis.com to read spreadsheet content (user-generated/untrusted data from third-party Google-hosted documents) which the agent then reads and could be influenced by, creating indirect prompt-injection risk.
- Audited
- Security analysis