fnl-ask
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read the
SKILL.mdfiles of target skills before describing them to the user. This creates a surface where instructions in those external files could theoretically influence the agent's output. However, the risk is mitigated because the skill is strictly restricted to providing recommendations and has tool invocations disabled. - [INGESTION_POINTS]: Target
SKILL.mdfiles on the local file system. - [BOUNDARY_MARKERS]: None specified in the instructions.
- [CAPABILITY_INVENTORY]: No file writing, network operations, or command execution capabilities are present or allowed;
disable-model-invocation: trueis set in the frontmatter. - [SANITIZATION]: None specified.
- [EXTERNAL_DOWNLOADS]: The skill references companion tools from external GitHub repositories, including those from Cloudflare and other community sources. The instructions explicitly direct the agent to 'install nothing yourself' and only provide the user with installation pointers, ensuring no automated remote code fetching occurs.
Audit Metadata