skills/bfollington/terma/sqlite-db/Gen Agent Trust Hub

sqlite-db

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation (SKILL.md) includes extensive examples of shell commands involving the sqlite3 CLI and mkdir. These commands are used to initialize databases, manage file structures, and execute SQL queries directly from the command line.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from SQLite databases into the agent's context, which represents a potential attack surface. Evidence chain: 1. Ingestion points: Output from sqlite3 queries is processed by the agent (SKILL.md). 2. Boundary markers: No specific delimiting instructions or "ignore embedded instructions" warnings are provided in the guide. 3. Capability inventory: The skill utilizes sqlite3 for file system access and data manipulation (SKILL.md). 4. Sanitization: The provided instructions do not include methods for sanitizing or escaping untrusted data processed through the database.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 06:00 PM