estimate-proposal

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gog CLI tool to perform operations on Google Sheets and Google Docs, including reading, updating, and creating documents.\n- [COMMAND_EXECUTION]: The skill includes a local validation script, scripts/verify_estimate_sheet.py, which executes the gog utility via Python's subprocess.run to verify spreadsheet integrity.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data sources to generate function inventories.\n
  • Ingestion points: As described in references/inventory-sources.md, the skill processes website URLs, RFP documents, meeting logs, and existing codebases.\n
  • Boundary markers: The instructions do not define specific delimiters or "ignore" directives for the external content processed.\n
  • Capability inventory: The skill has the capability to write to Google Workspace (via gog) and execute local scripts.\n
  • Sanitization: No explicit sanitization or validation of the external input content is mentioned before it is processed by the agent.\n- [DYNAMIC_EXECUTION]: The skill provides predefined Python one-liners in its reference documentation (e.g., references/deliverable-tooling.md) for the agent to execute locally to parse JSON output from temporary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 02:52 PM
Security Audit — agent-trust-hub — estimate-proposal