setup-chalk

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes untrusted data from a local repository (READMEs, configuration files, and source code). If these files contain malicious instructions, they could influence the agent's behavior during the analysis or generation phases. Ingestion points: README.md, package.json, source files (SKILL.md). Boundary markers: Absent. Capability inventory: Bash, Write, Read, Glob, Grep (SKILL.md). Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill requires the Bash tool to perform repository scans (grep, glob). While the instructions specify scanning tasks, the Bash tool provides a broad execution surface on untrusted file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 09:36 AM
Security Audit — agent-trust-hub — setup-chalk