audit-mcp-tool-friction

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown and YAML configuration metadata. It defines a methodology for auditing tool contracts and execution traces for usability issues.
  • [NO_CODE]: There are no scripts, binaries, or executable code fragments included in the skill files. It relies solely on natural language instructions to guide the agent's diagnostic behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze external tool schemas and execution traces (SKILL.md). While these are external data sources, the skill is limited to diagnostic reporting and does not possess capabilities (such as file writing or network access) that could be exploited via malicious data ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 03:38 PM