wiki-context

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes shell commands such as git rev-parse --show-toplevel to determine the project root and current workspace scope.
  • [EXTERNAL_DOWNLOADS]: Suggests the installation of a related skill using npx skills add dev-goraebap/agent-wiki-hub. This resource is owned by the same vendor as the skill author.
  • [PROMPT_INJECTION]: The skill processes untrusted data from local configuration files and environment metadata to determine agent context.
  • Ingestion points: Reads the .wiki/wiki-manifest.yaml file and extracts current Git branch names (e.g., feat/*, fix/*).
  • Boundary markers: None specified; the skill interprets the manifest structure directly to assemble document lists.
  • Capability inventory: The skill identifies and lists file paths and tags for the agent to subsequently read; it does not directly execute the content of the discovered documents.
  • Sanitization: No explicit validation or sanitization of the manifest content or branch strings is described in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 10:37 AM