current-slide

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, such as data exfiltration, command execution, or obfuscation, were detected. The skill's behavior is consistent with its stated purpose of improving context-awareness during development.
  • [PROMPT_INJECTION]: The skill relies on reading node_modules/.open-slide/current.json, which is an external data source. This represents an indirect prompt injection surface where a compromised status file could theoretically misdirect the agent's file operations.
  • Ingestion points: node_modules/.open-slide/current.json (specifically the pagePath and selection fields).
  • Boundary markers: Not specified; the agent is instructed to trust the file content for active navigation.
  • Capability inventory: The agent possesses file reading and editing capabilities (Read and Edit tools) which are used on the paths provided by the status file.
  • Sanitization: No specific input validation or sanitization of the JSON content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 05:39 AM
Security Audit — agent-trust-hub — current-slide