afk-compass

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill serves as a high-level router and decision-support tool. It provides a mapping of user needs to specific skill invocations (e.g., grill-me, wayfinder, afk-implement) without performing any actions itself. The instructions are purely navigational and intended to help the user manage their own workflow boundaries.
  • [NO_CODE]: Analysis of the skill files confirms there are no scripts, binaries, shell commands, or dynamic execution patterns. The functionality is restricted to natural language reasoning and recommendation based on the provided reference documents (frontend-crossroads.md and workflow-crossroads.md).
  • [INDIRECT_PROMPT_INJECTION]: While the skill analyzes the user's conversation to provide routing advice, it possesses no exploitable capabilities. It does not write to the filesystem, access the network, or execute code, which significantly limits the impact of any potential adversarial input in the conversation context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 04:09 AM