Skills
skills/l3digital-net/claude-code-plugins/wiki-sync/Gen Agent Trust Hub

wiki-sync

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard filesystem commands like mkdir, cp, and rm, along with a specialized CLI tool gh-manager, to manage wiki content. This is standard behavior for a synchronization tool.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes repository content to generate wiki pages. • Ingestion points: Reads from docs/, README.md, and source code (SKILL.md). • Boundary markers: No specific delimiters are used to isolate untrusted content (SKILL.md). • Capability inventory: Can modify files and push to a remote wiki (SKILL.md). • Sanitization: Lacks sanitization for embedded instructions (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:37 PM