wasm-gallery
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill allows the use of the
Bashtool, granting the agent the capability to execute arbitrary shell commands within the environment. - [EXTERNAL_DOWNLOADS]: The skill's primary function is to fetch and install WebAssembly binaries from an external community gallery using the
mcp__claude-flow__wasm_agent_createtool. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection (Category 8) because it retrieves and processes content from a community gallery.
- Ingestion points: Untrusted data enters the agent context via
mcp__claude-flow__wasm_gallery_listandmcp__claude-flow__wasm_gallery_search(SKILL.md). - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the gallery content.
- Capability inventory: The agent has high-impact capabilities including
Bashaccess and the ability to deploy executable WASM agents. - Sanitization: There is no evidence of sanitization or filtering of the gallery data before it is presented to the agent.
Audit Metadata