indexion-wiki

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a maintenance cycle where the agent reads project source files and wiki content, which constitutes an indirect prompt injection surface.
  • Ingestion points: The agent is instructed to read source files identified by the indexion wiki pages ingest command and the generated navigation file at .indexion/wiki/index.md.
  • Boundary markers: The documentation does not include specific boundary markers or instructions for the agent to ignore potentially malicious content within the ingested source files.
  • Capability inventory: The agent utilizes the indexion CLI tool to perform file writes, search index updates, and logging within the local .indexion/wiki/ directory.
  • Sanitization: The instructions do not define any sanitization or validation logic for the content extracted from the project's source files.
  • [COMMAND_EXECUTION]: The skill relies on the execution of the indexion CLI tool to manage the wiki's lifecycle.
  • The agent is directed to run multiple subcommands, such as pages add, pages update, index build, and plan reconcile, to maintain the manifest, markdown files, and search databases.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:04 AM
Security Audit — agent-trust-hub — indexion-wiki