surfacer

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill references the official surfacer repository at https://github.com/crafter-station/surfacer for installation instructions and uses a local surfacer binary to perform its tasks.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes .surfacer.json files which contain service mapping data. This represents an attack surface where maliciously crafted IR files could influence the agent's behavior.\n
  • Ingestion points: Service mapping files (.surfacer.json) processed by surfacer lint or used for compilation commands.\n
  • Boundary markers: None identified; the skill instructions do not provide explicit delimiters or warnings to treat IR content as untrusted data.\n
  • Capability inventory: The skill utilizes the Bash tool to execute surfacer binary commands.\n
  • Sanitization: No sanitization is performed at the skill level; the skill depends on the underlying binary for data processing.\n- [DYNAMIC_EXECUTION]: The tool is designed to generate executable code, including Bash scripts and Rust shims, from the provided IR mapping files. While this is the intended purpose, it involves the programmatic creation of executable content based on external inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 06:25 AM
Security Audit — agent-trust-hub — surfacer