lov-install-web-logo

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes command-line tools for installation and includes internal Python scripts to manage local configuration and validate the integrity of the skill source.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes existing project files such as metadata, manifests, and web assets, which serves as a potential ingestion point for untrusted data.
  • Ingestion points: Workflow steps in SKILL.md detail reading framework metadata and existing public assets.
  • Boundary markers: The skill uses explicit resolution logic for values but does not employ specific delimiters to isolate external file content from prompt instructions.
  • Capability inventory: The skill is capable of modifying local project source files and writing to its configuration file via scripts/profile_store.py.
  • Sanitization: The configuration management script implements a blocklist for sensitive metadata keys including 'token', 'secret', 'password', and 'apikey' to prevent credential exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 09:48 AM
Security Audit — agent-trust-hub — lov-install-web-logo