lov-legal-pages
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or behaviors were identified. The skill follows established security best practices for local agent tools.
- [SAFE]: The profile management script
scripts/profile_store.pyimplements restricted file permissions (0o600) and atomic write operations to protect user data from unauthorized access or corruption. - [SAFE]: The profile system includes an explicit check to prevent the storage of sensitive information such as passwords or API tokens, raising a ValueError if such fields are detected in the path segments.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests business facts provided by the user or project environment (Ingestion point: SKILL.md Workflow Step 1). It possesses the capability to write files and update website footers (Capability inventory: SKILL.md Workflow Steps 3 and 4). These risks are managed by workflow instructions that mandate explicit draft labeling, prohibit automatic protocol agreement, and require human verification of factual consistency (Sanitization/Boundaries: SKILL.md Workflow Steps 2 and 5).
Audit Metadata