planning-lob-gap-audit

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Google Docs and Sheets, which could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: Uses get_doc_as_markdown (Step 3, 4) and read_sheet_values (Step 1) to ingest content from project trackers and plan documents.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are used when interpolating this content into the analysis prompt.
  • Capability inventory: The skill has write access to Google Workspace via import_to_google_doc, create_spreadsheet, and modify_sheet_values (Step 8).
  • Sanitization: No explicit sanitization of document content is mentioned before processing.
  • [SAFE]: The skill accesses a configuration file from another skill located at ~/.claude/skills/admin-governance/references/lob-folder-map.md. This is a documented feature for synergy between tools by the same author to resolve folder mappings and does not involve sensitive credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 07:31 PM
Security Audit — agent-trust-hub — planning-lob-gap-audit