git-wiki

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is configured to automatically ingest and summarize project files to update its wiki without requesting user confirmation. This behavior creates an attack surface for indirect prompt injection where adversarial content within the repository could influence the agent's logic during documentation tasks.
  • Ingestion points: The skill reads from any git-tracked file in the repository, including source code and documentation.
  • Boundary markers: The instructions lack explicit delimitation or warnings to the agent to ignore instructions embedded in the project files.
  • Capability inventory: The skill has the capability to write and modify files within the .wiki/ directory.
  • Sanitization: No specific input validation or sanitization routines are defined for the repository content before it is summarized into the wiki.
  • [COMMAND_EXECUTION]: The skill instructions include the execution of standard git commands such as git rev-parse, git diff, and git ls-files. These are used to track project state and identify modified files for the purpose of updating the local wiki.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 08:06 PM
Security Audit — agent-trust-hub — git-wiki