skills/lancetw/skills/bible-bread/Gen Agent Trust Hub

bible-bread

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of an external companion skill and uses the uv package manager to manage dependencies and install browser binaries (chromium) via the patchright library for its data retrieval operations.
  • [COMMAND_EXECUTION]: Shell commands are utilized for path resolution, searching through local reference documents using grep and awk, and executing Python scripts with uv run to perform core tasks.
  • [PROMPT_INJECTION]: The skill ingests and processes text from external websites, creating an attack surface for indirect prompt injection. Ingestion points: Scripture data retrieved from Sefaria, BibleGateway, and FHL domains. Boundary markers: Retrieved text is placed within Markdown blockquote markers (>) in the devotional template. Capability inventory: The skill has access to shell execution (Bash), file modification (Write), and network access (WebFetch). Sanitization: There is no specific evidence of content validation or filtering of the retrieved external content before prompt interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 03:17 PM