markdown-to-sheets-presenter
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a Python script (
create_spreadsheet.py) that interacts with the Google Sheets API to create and format spreadsheets. - [DATA_EXFILTRATION]: The execution script reads
google-ads.yamlfrom the project root to retrieve sensitive OAuth credentials, including a refresh token, client ID, and client secret, which are then used to authenticate with Google's APIs. - [INDIRECT_PROMPT_INJECTION]: The skill parses and processes markdown reports (such as competitive analysis or performance reviews) which can contain untrusted data or embedded instructions from external sources.
- Ingestion points: Markdown content provided via file paths or extracted from conversation history as described in
SKILL.md(Step 1). - Boundary markers: None present; the skill's workflow instructions do not specify delimiters or warnings to ignore instructions embedded within the report content.
- Capability inventory: The skill possesses the capability to execute shell commands (
Bash), read files (Read), and perform network requests to Google APIs through the creation script. - Sanitization: No sanitization, escaping, or validation logic is applied to the input markdown before it is parsed and used to determine the spreadsheet structure and content.
- [EXTERNAL_DOWNLOADS]: The skill's setup process involves downloading scripts and configuration templates from the author's public GitHub repository (
github.com/fourteenwm/ppc-ai-skills).
Audit Metadata