skills/kusold/agent-skills/wiki-query/Gen Agent Trust Hub

wiki-query

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the raw/ and wiki/ directories, which are identified as ingestion points in SKILL.md. There are no explicit boundary markers or instructions to ignore embedded commands within these source files. The skill possesses capabilities to execute shell commands (rg) and write to the filesystem (wiki/analyses/). No sanitization or filtering of the external content is specified before it is interpolated into the agent's context or used to generate new wiki pages.- [COMMAND_EXECUTION]: The skill instructions include the use of the rg (ripgrep) command-line tool to perform searches within the wiki directory (rg -ni --fixed-strings -- "<term>" wiki/). While the use of --fixed-strings provides some protection against regex injection, this pattern involves executing shell commands with parameters derived from user queries.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:11 PM